© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126727
    Prev
    Next
    INDEX
    Explanations

    content

    np_max-act · gemini-2.0-flash

    instructions related to setting up and configuring software applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on tokens inside code‐or command‐block contexts (e.g. backtick fences, shell commands, and code snippets).

    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
     Elon
    -0.07
     Blades
    -0.06
    autoload
    -0.06
    OLT
    -0.06
    @Entity
    -0.06
    ям
    -0.06
    Jerry
    -0.06
     Δημο
    -0.06
    _pedido
    -0.06
    measure
    -0.06
    POSITIVE LOGITS
    .Details
    0.06
    =========
    0.06
     '''↵
    0.06
     miejs
    0.06
     Když
    0.06
    _EN
    0.06
    .Dep
    0.06
    adero
    0.06
     PAT
    0.06
    erais
    0.06
    Activations Density 0.039%

    No Known Activations