© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 69245
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emes
    -0.07
     visibly
    -0.07
    Filtered
    -0.07
     contribute
    -0.06
    URLRequest
    -0.06
     troubled
    -0.06
    ّ
    -0.06
     cottage
    -0.06
    ุก
    -0.06
     cumulative
    -0.06
    POSITIVE LOGITS
     Ngành
    0.06
    SEM
    0.06
    -split
    0.06
     Someone
    0.06
    Enh
    0.06
    ül
    0.06
    (Have
    0.06
    &W
    0.06
    (Self
    0.06
    /*----------------------------------------------------------------------------
    0.06
    Activations Density 0.002%

    No Known Activations