© 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. 90951
    Prev
    Next
    INDEX
    Explanations

    academic citations

    np_max-act · gemini-2.0-flash

    This neuron detects hedge and discourse-pivot words that introduce or qualify statements (e.g. one, such, given, potentially).

    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
     letz
    -0.07
     shrinking
    -0.06
     Evangel
    -0.06
    Tom
    -0.06
    umbn
    -0.06
     Chun
    -0.06
    BAD
    -0.06
    _cut
    -0.06
    َم
    -0.06
     yaptık
    -0.06
    POSITIVE LOGITS
     Seç
    0.06
    ©
    0.06
    §
    0.06
    esity
    0.06
     Syndrome
    0.06
    .Scanner
    0.06
     Leave
    0.06
     arbitration
    0.06
    nych
    0.06
     loss
    0.06
    Activations Density 0.069%

    No Known Activations