© 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. 3-RESID-POST-AA
    11. 94059
    Prev
    Next
    INDEX
    Explanations

    Semantics/Interpretation

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _DIALOG
    -0.07
     traj
    -0.07
     preceded
    -0.06
     continu
    -0.06
    it
    -0.06
     summons
    -0.06
    Ta
    -0.06
    .lp
    -0.06
    Zip
    -0.06
     LAW
    -0.06
    POSITIVE LOGITS
    อท
    0.07
     ویژ
    0.06
    photo
    0.06
    ımızı
    0.06
     Politico
    0.06
    düğü
    0.06
    AMED
    0.06
    FUNC
    0.06
    -prepend
    0.06
     medicinal
    0.06
    Activations Density 0.080%

    No Known Activations