© 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. 128806
    Prev
    Next
    INDEX
    Explanations

    party

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “third party” or related references to third‐party entities.

    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
     abortion
    -0.06
    xef
    -0.06
     Auschwitz
    -0.06
    itations
    -0.06
    olan
    -0.06
     Sanat
    -0.06
    wicklung
    -0.06
     Truman
    -0.06
     secretary
    -0.06
     jean
    -0.06
    POSITIVE LOGITS
     overrides
    0.07
    藥
    0.07
    	AND
    0.07
    ีส
    0.06
     expr
    0.06
     lie
    0.06
    余
    0.06
    [Z
    0.06
    PID
    0.06
     disclosing
    0.06
    Activations Density 0.005%

    No Known Activations