© 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. 126234
    Prev
    Next
    INDEX
    Explanations

    Chemical/drug research

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of how seizures are induced, especially phrases like “electrically induced,” “chemically induced,” or specific convulsant agents (e.g. pentylenetetrazole).

    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
     plight
    -0.07
     basis
    -0.06
     bacon
    -0.06
     report
    -0.06
    INE
    -0.06
     homogeneous
    -0.06
    nist
    -0.06
    Homepage
    -0.06
     уточ
    -0.06
    .domain
    -0.06
    POSITIVE LOGITS
    /dc
    0.06
    :y
    0.06
    ~↵↵
    0.06
     Rit
    0.06
    ué
    0.06
     twentieth
    0.06
    .coin
    0.06
    /;↵
    0.06
    -volume
    0.06
    _Space
    0.06
    Activations Density 0.078%

    No Known Activations