© 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. 126318
    Prev
    Next
    INDEX
    Explanations

    data loading/processing

    np_max-act · gemini-2.0-flash

    The neuron primarily detects occurrences of the “pre-” prefix in action words (e.g. preload, preloading, preconditioned).

    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
    .setUser
    -0.06
     뉴
    -0.06
     treason
    -0.06
    mtree
    -0.06
    ερι
    -0.06
    safe
    -0.06
    parity
    -0.06
    dataType
    -0.06
    .week
    -0.06
    grese
    -0.06
    POSITIVE LOGITS
     preload
    0.09
     redeem
    0.07
     preorder
    0.07
     preprocess
    0.07
    Prefab
    0.06
     whitelist
    0.06
     Frem
    0.06
    adm
    0.06
    A
    0.06
    _echo
    0.06
    Activations Density 0.018%

    No Known Activations