© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6326
    Prev
    Next
    INDEX
    Explanations

    -life

    np_max-act · gemini-2.0-flash

    This neuron detects occupational or role descriptors (e.g. titles like “historian,” “bishop,” “politician,” “director,” etc.) in disambiguation entries.

    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
     bondage
    -0.06
    して
    -0.06
    escription
    -0.06
    Behavior
    -0.06
    .com
    -0.06
    study
    -0.06
    269
    -0.06
    OH
    -0.06
    分
    -0.05
     inference
    -0.05
    POSITIVE LOGITS
     Karlov
    0.07
     lục
    0.07
    ylie
    0.07
    TextWriter
    0.06
    TextStyle
    0.06
     letterSpacing
    0.06
     ketogenic
    0.06
    upos
    0.06
     dvoj
    0.06
     TextStyle
    0.06
    Activations Density 0.066%

    No Known Activations