© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 49329
    Prev
    Next
    INDEX
    Explanations

    negative political rhetoric

    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
    แข
    -0.07
    ﾞﾞ
    -0.06
    高中
    -0.06
    arest
    -0.06
    FUL
    -0.06
    ده
    -0.06
     gaining
    -0.06
     namoro
    -0.06
     pocházet
    -0.06
    ère
    -0.06
    POSITIVE LOGITS
     inode
    0.07
    tm
    0.06
     conna
    0.06
    mv
    0.06
     DataColumn
    0.06
    ambia
    0.06
    .Parcel
    0.06
    .fn
    0.06
     drawback
    0.06
    cry
    0.05
    Activations Density 0.017%

    No Known Activations