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. 42332
    Prev
    Next
    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the word “people” (and similar social‐actor references).

    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
     Heritage
    -0.07
     대해서
    -0.07
     Worlds
    -0.06
     railways
    -0.06
     Ngân
    -0.06
     Thổ
    -0.06
     Rs
    -0.06
     truthful
    -0.06
     Refugee
    -0.06
    Strings
    -0.06
    POSITIVE LOGITS
     unborn
    0.06
    只要
    0.06
     decl
    0.06
    .o
    0.06
    ""
    0.06
    責
    0.06
    -break
    0.06
    ól
    0.06
     earliest
    0.06
    .adjust
    0.06
    Activations Density 0.066%

    No Known Activations