© 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. 126769
    Prev
    Next
    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash

    This neuron fires on JavaScript/TypeScript object‐literal property names (e.g. keys immediately before the “:”) in code.

    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
     MSNBC
    -0.06
    ��
    -0.06
     masturb
    -0.06
     clamp
    -0.06
    _band
    -0.06
    Opts
    -0.06
     rows
    -0.06
    ō
    -0.06
     yaptır
    -0.06
    jury
    -0.06
    POSITIVE LOGITS
     إل
    0.06
    ----</
    0.06
    _UUID
    0.06
    /img
    0.06
    .currentState
    0.06
    _ALREADY
    0.05
     помощью
    0.05
     mt
    0.05
    .TextChanged
    0.05
    .Inter
    0.05
    Activations Density 0.024%

    No Known Activations