© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 64930
    Prev
    Next
    INDEX
    Explanations

    Non-English language

    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
    Negative Logits
     网
    -0.06
    ::
    -0.06
     besten
    -0.06
     उम
    -0.06
     çeşitli
    -0.06
     Consider
    -0.06
    ]));↵
    -0.06
     العرب
    -0.06
     cx
    -0.06
    =str
    -0.06
    POSITIVE LOGITS
    .embed
    0.08
    руг
    0.07
     demol
    0.07
    cola
    0.07
    ीन
    0.07
    rome
    0.07
    loid
    0.07
    edin
    0.07
    един
    0.07
    Translator
    0.07
    Activations Density 0.328%

    No Known Activations