© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 127221
    Prev
    Next
    INDEX
    Explanations

    "},"

    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
    และม
    -0.06
    ‎
    -0.06
     люб
    -0.06
    ιά
    -0.06
    &);↵↵
    -0.06
     lebih
    -0.06
     situace
    -0.06
    бира
    -0.06
     Authority
    -0.06
    yum
    -0.06
    POSITIVE LOGITS
    _VERTICAL
    0.07
     OT
    0.07
    isel
    0.06
    _LONG
    0.06
    bolt
    0.06
    .keyCode
    0.06
    IconModule
    0.06
    amera
    0.06
     RaycastHit
    0.06
    _WEEK
    0.06
    Activations Density 0.012%

    No Known Activations