© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6729
    Prev
    Next
    INDEX
    Explanations

    Titles

    np_max-act · gemini-2.0-flash

    It detects honorifics and formal titles (e.g. Dr., Capt., Gen., H.E., Maj. Gen., Datuk) that precede names.

    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
    Library
    -0.07
    、ア
    -0.07
    ज
    -0.07
    歷
    -0.06
    _blocks
    -0.06
    技术
    -0.06
    移動
    -0.06
    Arizona
    -0.06
     cub
    -0.06
     Netflix
    -0.06
    POSITIVE LOGITS
    GORITHM
    0.08
     fright
    0.07
    (fill
    0.06
     OPER
    0.06
    .kafka
    0.06
    Dr
    0.06
     Dr
    0.06
     ASTM
    0.06
     delim
    0.06
    ATFORM
    0.06
    Activations Density 0.007%

    No Known Activations