© 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. 7235
    Prev
    Next
    INDEX
    Explanations

    Random text

    np_max-act · gemini-2.0-flash

    content related to medical sales strategies.

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

    This neuron detects structural outline markers—especially list and section numbers (e.g. “1”, “2”, “3” and their following punctuation) in a document.

    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
    Checkpoint
    -0.07
     Checked
    -0.06
    REL
    -0.06
     Airways
    -0.06
    ulence
    -0.06
    .DateTimeField
    -0.06
    ipel
    -0.06
     Facility
    -0.06
    REAL
    -0.06
     skepticism
    -0.06
    POSITIVE LOGITS
    .help
    0.07
     ens
    0.06
     Країна
    0.06
    ━�
    0.06
     ­
    0.06
     whereabouts
    0.06
     yytype
    0.06
     Linkedin
    0.06
     salida
    0.06
    retweeted
    0.05
    Activations Density 0.418%

    No Known Activations