© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44347
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    np_max-act · gemini-2.0-flash

    This neuron fires on past-tense action verbs that describe changes in state or movement (e.g., “progressed,” “transitioned,” “moved,” “evolved”).

    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
    ительное
    -0.07
     un
    -0.06
     Authorization
    -0.06
     ideal
    -0.06
    ;
    ↵
    ↵
    ↵
    -0.06
     aday
    -0.06
     Herrera
    -0.06
     cheeks
    -0.06
     ),↵↵
    -0.06
     ohne
    -0.06
    POSITIVE LOGITS
    Descriptions
    0.06
    REATED
    0.06
     Fé
    0.06
     Rene
    0.06
    .setProgress
    0.06
    宿
    0.06
     picked
    0.06
    署
    0.06
    .createNew
    0.06
     orchestrated
    0.06
    Activations Density 0.193%

    No Known Activations