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. 11-RESID-POST-AA
    6. 18268
    Prev
    Next
    INDEX
    Explanations

    Providing help/information

    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_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
     ldb
    -0.07
     sailor
    -0.06
    jh
    -0.06
    ico
    -0.06
    sth
    -0.06
    CompleteListener
    -0.06
    JNI
    -0.06
    awah
    -0.06
     cof
    -0.06
    /view
    -0.06
    POSITIVE LOGITS
    _TBL
    0.07
     misrepresented
    0.07
    .Appearance
    0.07
    лика
    0.06
    .HORIZONTAL
    0.06
     Nude
    0.06
     Investments
    0.06
     Minority
    0.06
    Performance
    0.06
     Bauer
    0.06
    Activations Density 0.144%

    No Known Activations