© 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. 30111
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of the RL “state” concept (and related MDP notation) in the mathematical definition.

    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
    وش
    -0.06
     있었다
    -0.06
    fig
    -0.06
    ماری
    -0.06
    `;↵
    -0.06
    Intro
    -0.06
    ESP
    -0.06
     scam
    -0.06
     defendants
    -0.06
    _rate
    -0.06
    POSITIVE LOGITS
     MADE
    0.07
     regarding
    0.06
    -reader
    0.06
    斗
    0.06
    Regarding
    0.06
     Trout
    0.06
    elsey
    0.06
     stron
    0.06
    (old
    0.06
    まと
    0.06
    Activations Density 0.012%

    No Known Activations