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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19-RESID-POST-AA
    6. 54347
    Prev
    Next
    INDEX
    Explanations

    code, error messages

    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
    								↵
    -0.08
    .onNext
    -0.07
    snd
    -0.07
    _#{
    -0.06
    _pag
    -0.06
    ห
    -0.06
    _asc
    -0.06
    .Enqueue
    -0.06
    ?t
    -0.06
    NSSet
    -0.06
    POSITIVE LOGITS
     midnight
    0.07
    ileş
    0.07
    атки
    0.06
    direction
    0.06
     Merrill
    0.06
    _perm
    0.06
    湯
    0.06
    meth
    0.06
    уш
    0.06
    �니다
    0.06
    Activations Density 0.000%

    No Known Activations