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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RESID-POST-AA
    6. 93242
    Prev
    Next
    INDEX
    Explanations

    Sports field goal attempts

    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
    –↵↵
    -0.08
    еся
    -0.07
     }];↵↵
    -0.07
    >();↵↵
    -0.07
    PopMatrix
    -0.07
    警察
    -0.06
    ué
    -0.06
    picture
    -0.06
    Update
    -0.06
    (sn
    -0.06
    POSITIVE LOGITS
     Girlfriend
    0.07
     Glass
    0.07
    /her
    0.06
    成本
    0.06
     shareholders
    0.06
     encount
    0.06
     pend
    0.06
     تز
    0.06
    infeld
    0.06
    typically
    0.06
    Activations Density 0.002%

    No Known Activations