© 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. 93411
    Prev
    Next
    INDEX
    Explanations

    theories and basis

    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
    )'
    -0.07
    rak
    -0.07
     som
    -0.07
    โดย
    -0.06
     �
    -0.06
     Corn
    -0.06
     Som
    -0.06
    .range
    -0.06
    Dock
    -0.06
    普
    -0.06
    POSITIVE LOGITS
     О
    0.07
    _Move
    0.07
    저
    0.07
    izzare
    0.07
    .constructor
    0.07
     Organizer
    0.07
    ционные
    0.07
     frag
    0.06
    .change
    0.06
    AGIC
    0.06
    Activations Density 0.010%

    No Known Activations