© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 113181
    Prev
    Next
    INDEX
    Explanations

    creating/loading

    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
     pill
    -0.06
    bounds
    -0.06
     FK
    -0.06
     Therm
    -0.06
    Rob
    -0.06
     mound
    -0.06
    po
    -0.06
     sl
    -0.06
    ší
    -0.06
     Wein
    -0.06
    POSITIVE LOGITS
    .gov
    0.08
     Chemistry
    0.07
     ########.
    0.07
    _PRIVATE
    0.07
    _ITEMS
    0.06
    unctuation
    0.06
    $table
    0.06
    .Tasks
    0.06
    -interface
    0.06
    _bind
    0.06
    Activations Density 0.047%

    No Known Activations