© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6980
    Prev
    Next
    INDEX
    Explanations

    communication and abstract ideas

    np_max-act · gemini-2.0-flash

    This neuron is effectively “dead” (never activates) and so does not 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
     produced
    -0.07
     cycling
    -0.07
     discuss
    -0.06
     DUP
    -0.06
     ký
    -0.06
     came
    -0.06
     Aunt
    -0.06
    PATH
    -0.06
     realism
    -0.06
    ensing
    -0.06
    POSITIVE LOGITS
    ционный
    0.07
    ें↵↵
    0.07
     giữ
    0.07
    ([('
    0.07
    73
    0.06
    :M
    0.06
    /Library
    0.06
    SerializeField
    0.06
    CRE
    0.06
    ὶ
    0.06
    Activations Density 0.124%

    No Known Activations