© 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. 92157
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    This neuron flags user-side enumeration requests—specifically tokens like “each” (and related list-specifying words) that signal “for each …” in a question.

    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
    顶
    -0.07
    daemon
    -0.06
     COLUMN
    -0.06
    Eye
    -0.06
    Runs
    -0.06
     Yet
    -0.06
    otes
    -0.06
    iris
    -0.06
    Tank
    -0.06
    '];?>
    -0.06
    POSITIVE LOGITS
     PyTuple
    0.07
     ],↵
    0.06
     nilai
    0.06
    :UIButtonType
    0.06
    选�
    0.06
     र
    0.06
     DRIVE
    0.06
     indeb
    0.06
    _marshaled
    0.06
     stdClass
    0.06
    Activations Density 0.047%

    No Known Activations