© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92446
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the GNU Scientific Library (GSL) API (e.g. “gsl::vector,” “_calloc,” “_memcpy,” etc.).

    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
     satisfactory
    -0.07
     @"";↵
    -0.06
     kisses
    -0.06
    _POWER
    -0.06
    UILD
    -0.06
     calendar
    -0.06
    XYZ
    -0.06
    -business
    -0.06
    绿
    -0.06
     Eaton
    -0.06
    POSITIVE LOGITS
    .crt
    0.07
     नक
    0.07
     зан
    0.06
     pada
    0.06
    	fclose
    0.06
    configs
    0.06
    ')");↵
    0.06
     debunk
    0.06
     drafted
    0.06
    '>";↵
    0.06
    Activations Density 0.113%

    No Known Activations