© 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. 68932
    Prev
    Next
    INDEX
    Explanations

    filled

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens—it remains inactive and thus doesn’t detect any pattern.

    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
    (docs
    -0.07
    foreach
    -0.07
    Ultimately
    -0.07
    (states
    -0.07
    (movie
    -0.06
     pornô
    -0.06
     coatings
    -0.06
     wander
    -0.06
    Od
    -0.06
     novice
    -0.06
    POSITIVE LOGITS
    ]=$
    0.07
     appropriation
    0.07
    DTV
    0.07
    端
    0.07
     الناس
    0.06
    GGLE
    0.06
    LIB
    0.06
    65
    0.06
    res
    0.06
     GI
    0.06
    Activations Density 0.011%

    No Known Activations