© 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. 128613
    Prev
    Next
    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash

    The neuron activates strongly on phrasal verbs that end with the particle “up,” e.g. “pick up.”

    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
     Kan
    -0.07
    rende
    -0.07
     escorted
    -0.07
     hồ
    -0.06
    ango
    -0.06
     revert
    -0.06
    amar
    -0.06
    _issue
    -0.06
    救
    -0.06
     Laur
    -0.06
    POSITIVE LOGITS
     sizable
    0.06
    NegativeButton
    0.06
    (tag
    0.06
     DET
    0.06
     содерж
    0.06
    لع
    0.06
    .MaxValue
    0.06
    ASHINGTON
    0.06
     broadcasters
    0.06
     Torah
    0.06
    Activations Density 0.124%

    No Known Activations