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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 46304
    Prev
    Next
    INDEX
    Explanations

    ents

    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
     شروع
    -0.07
     能
    -0.07
    是在
    -0.06
    >alert
    -0.06
     bdsm
    -0.06
    (Book
    -0.06
    .SelectedValue
    -0.06
    >{"
    -0.06
     
    -0.06
     şekil
    -0.06
    POSITIVE LOGITS
     receiver
    0.07
    Side
    0.07
    ambient
    0.07
    ocz
    0.07
     monarchy
    0.07
     boost
    0.07
    Orm
    0.07
     dancers
    0.07
     path
    0.07
     Dw
    0.06
    Activations Density 0.025%

    No Known Activations