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. 15-RESID-POST-AA
    6. 102508
    Prev
    Next
    INDEX
    Explanations

    pixel

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proposals
    -0.07
     LIMITED
    -0.06
     constrained
    -0.06
     Π
    -0.06
     یک
    -0.06
    جي
    -0.06
    atatype
    -0.06
    เร
    -0.06
    테
    -0.06
    chef
    -0.06
    POSITIVE LOGITS
    .gsub
    0.07
     
    0.06
     nokt
    0.06
    (getApplicationContext
    0.06
    abee
    0.06
    ….
    0.06
    _FULLSCREEN
    0.06
    />.
    0.06
    .DropTable
    0.06
     stran
    0.06
    Activations Density 0.082%

    No Known Activations