© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92265
    Prev
    Next
    INDEX
    Explanations

    Coding questions

    np_max-act · gemini-2.0-flash

    The neuron fires on first‐person narrative phrases in questions (e.g. “I’ve started,” “I took over,” “we’ve been given”) that describe the asker’s own actions or context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    introductory first-person context about recently starting, taking over, or working on a project/job for a client or friend.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noted
    -0.06
     recruiter
    -0.06
     economy
    -0.06
    .tmp
    -0.06
     homicide
    -0.06
    ORITY
    -0.06
     foundation
    -0.06
    nul
    -0.06
    imary
    -0.06
    _PEER
    -0.06
    POSITIVE LOGITS
    .faces
    0.08
     Pretty
    0.06
     gut
    0.06
     застос
    0.06
    .Raise
    0.06
     xhttp
    0.06
    	lines
    0.06
     boils
    0.06
    /load
    0.06
    .tm
    0.06
    Activations Density 0.065%

    No Known Activations