© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109854
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron flags tokens that occur as part of section‐heading labels or rule/instruction markers (e.g. “Rule:”, “Remover”, “Escolher”) in prompt headers.

    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
     созда
    -0.08
    _RADIUS
    -0.07
     نوش
    -0.07
    OLD
    -0.06
    projection
    -0.06
    -thumbnail
    -0.06
    _repository
    -0.06
     절
    -0.06
    itia
    -0.06
    СТ
    -0.06
    POSITIVE LOGITS
     Chancellor
    0.07
    ายใน
    0.06
     ApplicationController
    0.06
     qualified
    0.06
    mino
    0.06
     información
    0.06
    iven
    0.06
    ール
    0.06
    _lua
    0.06
     denomination
    0.06
    Activations Density 0.012%

    No Known Activations