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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 9739
    Prev
    Next
    INDEX
    Explanations

    Chemical formulas

    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
     verses
    -0.06
    ήμερα
    -0.06
     bunu
    -0.06
    ozí
    -0.06
    (coeffs
    -0.06
    สถ
    -0.06
    .MEDIA
    -0.06
    �i
    -0.06
    ,不过
    -0.05
     |-
    -0.05
    POSITIVE LOGITS
     RECEIVE
    0.07
     literal
    0.07
     DecimalFormat
    0.07
    引用频次
    0.06
    pees
    0.06
    bank
    0.06
    flag
    0.06
    eful
    0.06
     exc
    0.06
    (predicate
    0.06
    Activations Density 0.065%

    No Known Activations