Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 57729
    Prev
    Next
    INDEX
    Explanations

    in vitro biological processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     рук
    -0.06
     titular
    -0.06
    dığ
    -0.06
     Copp
    -0.06
     '\\
    -0.06
    _control
    -0.06
     coisa
    -0.06
    sets
    -0.06
    „N
    -0.06
    :*
    -0.06
    POSITIVE LOGITS
    CEED
    0.07
     PropertyValue
    0.06
     refund
    0.06
    acerb
    0.06
    adians
    0.06
    _dem
    0.06
    증금
    0.06
     behaved
    0.06
    .Receive
    0.06
    edd
    0.06
    Activations Density 0.051%

    No Known Activations