© 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. 11-RESID-POST-AA
    6. 36877
    Prev
    Next
    INDEX
    Explanations

    understanding

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ità
    -0.08
     challeng
    -0.07
     prevented
    -0.07
     RegExp
    -0.07
    Supported
    -0.07
     without
    -0.07
     ice
    -0.07
    January
    -0.06
    働
    -0.06
    Extended
    -0.06
    POSITIVE LOGITS
     شود
    0.06
    .mail
    0.06
    ?a
    0.06
    ۀ
    0.06
    'nin
    0.06
    .Exists
    0.06
     наблю
    0.06
    krv
    0.06
     چگونه
    0.05
     vượt
    0.05
    Activations Density 0.026%

    No Known Activations