© 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. 18211
    Prev
    Next
    INDEX
    Explanations

    gain

    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
    letics
    -0.07
     Madame
    -0.07
     Fantastic
    -0.07
    inalg
    -0.07
     ortadan
    -0.06
    Oh
    -0.06
     robbery
    -0.06
    anal
    -0.06
    mind
    -0.06
     coloured
    -0.06
    POSITIVE LOGITS
    JI
    0.07
     наб
    0.07
    Sym
    0.06
    Perm
    0.06
     aug
    0.06
    们
    0.06
    .extra
    0.06
     perso
    0.06
    ?type
    0.06
    济
    0.06
    Activations Density 0.011%

    No Known Activations