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. 27245
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    np_max-act · gemini-2.0-flash

    This neuron remains inactive (zero‐activation) on every token, indicating it doesn’t detect any specific pattern.

    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
    Expansion
    -0.07
    岁
    -0.07
    ські
    -0.07
    _answers
    -0.07
     guru
    -0.06
    ivar
    -0.06
    строй
    -0.06
    .har
    -0.06
    вет
    -0.06
     оп
    -0.06
    POSITIVE LOGITS
     Xã
    0.07
     Mix
    0.07
     emb
    0.06
    ban
    0.06
    _OPER
    0.06
     taj
    0.06
    $MESS
    0.06
     zaj
    0.06
     lecken
    0.06
    ;")↵
    0.06
    Activations Density 0.031%

    No Known Activations