© 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. 29481
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    conversations involving playful or humorous themes related to farting.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect spelled‐out ordinal numbers (e.g. “third,” “fourth,” “fifth,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     al
    -0.07
    rani
    -0.07
     numeric
    -0.06
     semana
    -0.06
     membr
    -0.06
     enforcement
    -0.06
     anth
    -0.06
     Ibrahim
    -0.06
    VertexAttrib
    -0.06
     Americ
    -0.06
    POSITIVE LOGITS
    =no
    0.07
    uating
    0.06
     확실
    0.06
     movable
    0.06
    ={}
    0.06
     νε
    0.06
     hóa
    0.06
     перек
    0.06
    anson
    0.06
    ↵↵↵↵↵↵
    0.06
    Activations Density 0.123%

    No Known Activations