© 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
    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. 18098
    Prev
    Next
    INDEX
    Explanations

    isolated

    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
     Saturday
    -0.07
    ']",
    -0.06
    (timer
    -0.06
     Ginger
    -0.06
    90
    -0.06
     wheel
    -0.06
    Bounding
    -0.06
    .setAction
    -0.06
    	min
    -0.06
    or
    -0.06
    POSITIVE LOGITS
    .protobuf
    0.06
    웨디시
    0.06
    dbg
    0.06
    _ws
    0.06
    暗
    0.06
    acd
    0.06
    _SIGNATURE
    0.06
    _.
    0.06
     uč
    0.06
    أك
    0.06
    Activations Density 0.007%

    No Known Activations