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. 31426
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
     Presence
    -0.07
     Detailed
    -0.07
    idi
    -0.07
    Security
    -0.07
    .When
    -0.06
    illin
    -0.06
    速
    -0.06
     smoothing
    -0.06
     götür
    -0.06
    ека
    -0.06
    POSITIVE LOGITS
    BUTTONDOWN
    0.07
    _LOADED
    0.07
    理
    0.07
     Paginator
    0.06
    ">--}}↵
    0.06
    ुट
    0.06
    "
    ↵
    ↵
    ↵
    0.06
    _increment
    0.06
     ngang
    0.06
     मत
    0.06
    Activations Density 0.014%

    No Known Activations