Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 60933
    Prev
    Next
    INDEX
    Explanations

    JoinColumn

    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
    Not in Any Lists

    No Comments

    Negative Logits
     corpor
    -0.07
     быть
    -0.06
    .training
    -0.06
     oversh
    -0.06
     stationary
    -0.06
    categorie
    -0.06
     imagen
    -0.06
    記事
    -0.06
    BILE
    -0.06
    女子
    -0.06
    POSITIVE LOGITS
    SerializedName
    0.07
     fprintf
    0.07
    !.↵↵
    0.07
     JO
    0.06
    JoinColumn
    0.06
     Bridge
    0.06
     สามารถ
    0.06
    若
    0.06
     <<"
    0.06
     이렇게
    0.06
    Activations Density 0.002%

    No Known Activations