© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 1474
    Prev
    Next
    INDEX
    Explanations

    of

    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
    츠
    -0.07
    sında
    -0.06
     で
    -0.06
     ฮ
    -0.06
     boyfriend
    -0.06
     جور
    -0.06
    **)
    -0.06
    [id
    -0.06
    で
    -0.06
    -Based
    -0.06
    POSITIVE LOGITS
     Mounted
    0.07
    权限
    0.06
     Ange
    0.06
    .ExecuteScalar
    0.06
     �
    0.06
     Duel
    0.06
    μένων
    0.06
     filib
    0.06
    bidden
    0.06
     sním
    0.06
    Activations Density 0.043%

    No Known Activations