© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89324
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron activates on the token “possible,” flagging mentions of whether something is or isn’t feasible.

    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
    queueReusableCell
    -0.06
    追加
    -0.06
     hacen
    -0.06
     corrobor
    -0.06
     Monday
    -0.06
    those
    -0.06
    023
    -0.06
    余
    -0.06
     reduction
    -0.06
    ятся
    -0.06
    POSITIVE LOGITS
     abdom
    0.08
    for
    0.07
    <Role
    0.07
    ifax
    0.07
    (dp
    0.07
    .anim
    0.07
    .getLocation
    0.07
    ordin
    0.07
    /run
    0.07
    Fort
    0.07
    Activations Density 0.029%

    No Known Activations