© 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. 23-RESID-POST-AA
    11. 7666
    Prev
    Next
    INDEX
    Explanations

    Um

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мих
    -0.06
    очно
    -0.06
    抽
    -0.06
     strife
    -0.06
     chicken
    -0.06
     controllers
    -0.06
     Cynthia
    -0.05
    ávací
    -0.05
     Pasta
    -0.05
     HISTORY
    -0.05
    POSITIVE LOGITS
     Um
    0.08
    _DEAD
    0.07
     uh
    0.07
    ?>"
    0.07
    missible
    0.07
    .Throw
    0.07
     ヾ
    0.07
     "))
    0.07
    ,no
    0.07
    .ex
    0.07
    Activations Density 0.007%

    No Known Activations