© 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. 51964
    Prev
    Next
    INDEX
    Explanations

    chess

    np_max-act · gemini-2.0-flash

    The neuron fires on the analytic chess‐commentary vocabulary—words describing move objectives (develops, prepares, controls, center, knight, bishop, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    chess moves and openings related to knight positions.

    oai_token-act-pair · gpt-4o-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
    对于
    -0.07
    .toHexString
    -0.06
     crossings
    -0.06
     меропри
    -0.06
    (member
    -0.06
    .Marshal
    -0.06
     motifs
    -0.06
     předsed
    -0.06
    ML
    -0.06
     คำ
    -0.06
    POSITIVE LOGITS
    Pull
    0.07
     tôi
    0.07
    .Part
    0.06
    guid
    0.06
    reve
    0.06
     Jesse
    0.06
    pués
    0.06
     Public
    0.06
     Valley
    0.06
    국의
    0.06
    Activations Density 0.006%

    No Known Activations