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. 11-RESID-POST-AA
    6. 42200
    Prev
    Next
    INDEX
    Explanations

    suggestions and recommendations

    np_max-act · gemini-2.0-flash

    This neuron detects requests for recommendations or suggestions (e.g., asking “could you recommend any good places to check out?”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    港
    -0.07
    ा:
    -0.07
     religions
    -0.07
     getNode
    -0.06
    eb
    -0.06
     bakım
    -0.06
     другие
    -0.06
    ounce
    -0.06
     grit
    -0.06
    Чтобы
    -0.06
    POSITIVE LOGITS
    重複重複
    0.06
    _COLS
    0.06
    划
    0.06
    entionPolicy
    0.06
     OCR
    0.06
    }';↵
    0.06
    €™
    0.06
    _FRAME
    0.06
     crud
    0.06
    џЭ
    0.06
    Activations Density 0.027%

    No Known Activations