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. 21124
    Prev
    Next
    INDEX
    Explanations

    Medical statistics

    np_max-act · gemini-2.0-flash

    The neuron detects small numeric values—especially sample‐size or “n=” counts—presented in parentheses within the text.

    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
    OSP
    -0.07
     newRow
    -0.06
    -century
    -0.06
    /exp
    -0.06
     "
    -0.06
    eny
    -0.06
    ofile
    -0.06
     spinning
    -0.06
    נ
    -0.06
    ΡΑ
    -0.06
    POSITIVE LOGITS
    Imports
    0.07
    してる
    0.07
    /.↵
    0.06
    #undef
    0.06
    @implementation
    0.06
    -controls
    0.06
     Garmin
    0.06
    ({});↵
    0.06
    Oregon
    0.06
    :I
    0.06
    Activations Density 0.329%

    No Known Activations