© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 51956
    Prev
    Next
    INDEX
    Explanations

    cursor

    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
     treaties
    -0.07
    .TEXT
    -0.06
    .component
    -0.06
    dd
    -0.06
     republice
    -0.06
    OP
    -0.06
     HuffPost
    -0.06
     foes
    -0.06
    κης
    -0.06
     litt
    -0.06
    POSITIVE LOGITS
    }*/↵↵
    0.06
     exclaimed
    0.06
     Census
    0.06
    =default
    0.06
    852
    0.06
    approx
    0.06
    ...',
    0.06
     جمهوری
    0.06
    earned
    0.06
     datos
    0.06
    Activations Density 0.002%

    No Known Activations