© 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. 7-RESID-POST-AA
    11. 32221
    Prev
    Next
    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    Tokens that indicate identifier or field names — i.e., name-related identifiers in code and documentation.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CR
    -0.08
    OC
    -0.07
     Cruc
    -0.07
     difíc
    -0.07
    expl
    -0.07
    Quite
    -0.07
    CU
    -0.07
     C
    -0.07
    CEL
    -0.07
    C
    -0.06
    POSITIVE LOGITS
     Name
    0.16
    name
    0.16
     name
    0.16
    Name
    0.13
     names
    0.12
    -name
    0.12
    .name
    0.11
    名
    0.10
    _name
    0.10
     Names
    0.10
    Activations Density 0.176%

    No Known Activations