© 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. 41481
    Prev
    Next
    INDEX
    Explanations

    + or -

    np_max-act · gemini-2.0-flash

    The neuron fires on Apache htaccess “Options” directives that enable or disable features (lines beginning with “Options” with +/– flags).

    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
     Chronicles
    -0.07
    EFF
    -0.07
    igor
    -0.07
     Remarks
    -0.07
    نتی
    -0.06
     Shorts
    -0.06
    ichi
    -0.06
     DAY
    -0.06
     Mistress
    -0.06
    व
    -0.06
    POSITIVE LOGITS
     mús
    0.07
     aes
    0.06
     adhere
    0.06
    _HELP
    0.06
    +S
    0.06
     kept
    0.06
    ượng
    0.06
    532
    0.06
     moh
    0.06
    185
    0.06
    Activations Density 0.003%

    No Known Activations