© 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. 92044
    Prev
    Next
    INDEX
    Explanations

    Incomplete texts

    np_max-act · gemini-2.0-flash

    This neuron detects biographical background details—phrases describing a person’s personal life, origins, relationships, or profile information.

    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
    ケット
    -0.07
     ülke
    -0.07
    requete
    -0.06
    (Camera
    -0.06
    ιβ
    -0.06
     ارائه
    -0.06
     clothes
    -0.06
     Angel
    -0.06
    (Box
    -0.06
    ita
    -0.06
    POSITIVE LOGITS
     směrem
    0.06
    "in
    0.06
     microwave
    0.06
    *******/↵↵
    0.06
    やす
    0.06
     INF
    0.06
     situaci
    0.06
     né
    0.06
    )/(
    0.06
     electromagnetic
    0.06
    Activations Density 0.279%

    No Known Activations