© 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. 7-RESID-POST-AA
    11. 91410
    Prev
    Next
    INDEX
    Explanations

    distance

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _insert
    -0.08
     Hughes
    -0.08
     flights
    -0.08
    .nombre
    -0.06
    overn
    -0.06
     neighbors
    -0.06
     Meadows
    -0.06
    ku
    -0.06
    ovies
    -0.06
     SimpleName
    -0.06
    POSITIVE LOGITS
    sl
    0.07
     },
    0.07
    =None
    0.07
    (base
    0.07
    ){
    0.06
    _FRAME
    0.06
     TSRMLS
    0.06
    .pm
    0.06
    TERM
    0.06
    <Expression
    0.06
    Activations Density 0.014%

    No Known Activations