© 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. 85685
    Prev
    Next
    INDEX
    Explanations

    must

    np_max-act · gemini-2.0-flash

    This neuron spots obligation phrases—specifically modal “must” (and similar) constructions that set required conditions (e.g. “must be unused,” “must be accompanied,” “must contact”) in policy or instruction text.

    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
     yacc
    -0.07
     ListTile
    -0.07
    لان
    -0.07
     filho
    -0.06
    later
    -0.06
    Grade
    -0.06
     prisoner
    -0.06
    cü
    -0.06
     tvoří
    -0.06
    History
    -0.06
    POSITIVE LOGITS
     Apost
    0.07
     bats
    0.07
     rõ
    0.07
    -trade
    0.06
     Aaron
    0.06
    trace
    0.06
    Cash
    0.06
     rigid
    0.06
     plugged
    0.06
     Ticaret
    0.06
    Activations Density 0.022%

    No Known Activations