© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55598
    Prev
    Next
    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash

    The neuron activates on auxiliary and modal verbs (e.g., “can,” “will,” “has,” “seems”) that signal ability, possibility, or description.

    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
    ischer
    -0.07
    FragmentManager
    -0.07
     humili
    -0.06
     kişinin
    -0.06
    grp
    -0.06
     ticker
    -0.06
    ९
    -0.06
     silky
    -0.06
    encoder
    -0.06
     dav
    -0.06
    POSITIVE LOGITS
     Ebony
    0.07
     PART
    0.06
    нее
    0.06
    {},↵
    0.06
    />
    ↵
    0.06
    ought
    0.06
    (Local
    0.06
     ####
    0.06
     mango
    0.06
     看
    0.06
    Activations Density 0.229%

    No Known Activations