© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 48679
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    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
    Rub
    -0.08
    datetime
    -0.07
    aviest
    -0.07
    サイト
    -0.06
    間
    -0.06
    验证
    -0.06
    today
    -0.06
     ~/.
    -0.06
    ære
    -0.06
    _routes
    -0.06
    POSITIVE LOGITS
     ApplicationUser
    0.07
     Outdoor
    0.06
     För
    0.06
     Overflow
    0.06
    cents
    0.06
     Reed
    0.06
    @NgModule
    0.06
    %%
    0.05
    <|start_header_id|>
    0.05
     μον
    0.05
    Activations Density 0.139%

    No Known Activations