© 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. 51959
    Prev
    Next
    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash

    responses that reflect or challenge societal norms about gender roles and equality.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is primarily responsive to negation words (contractions like “don’t”/“doesn’t”), flagging negative or refusal phrasing.

    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
    -independent
    -0.06
     ovarian
    -0.06
    UNCTION
    -0.06
     dic
    -0.06
     glyph
    -0.06
    林
    -0.06
    While
    -0.06
     Charging
    -0.06
    قول
    -0.06
     motorcycle
    -0.06
    POSITIVE LOGITS
    _vm
    0.07
     محدود
    0.07
    (namespace
    0.06
    -hidden
    0.06
    _PO
    0.06
    310
    0.06
     condemned
    0.06
     đốc
    0.06
     y
    0.06
     stmt
    0.06
    Activations Density 0.018%

    No Known Activations