Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 10210
    Prev
    Next
    INDEX
    Explanations

    を

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cub
    -0.07
     Sign
    -0.06
     sign
    -0.06
     bilingual
    -0.06
     Culture
    -0.06
     Biden
    -0.06
     licenses
    -0.06
     recibir
    -0.06
     Equal
    -0.06
     Parents
    -0.06
    POSITIVE LOGITS
    []>(
    0.09
     Kurulu
    0.06
    만남
    0.06
    .UNKNOWN
    0.06
     Pieces
    0.06
    できない
    0.06
    ();?>
    0.06
    -pagination
    0.06
    ?:
    0.06
     convertView
    0.06
    Activations Density 0.014%

    No Known Activations