© 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. 8864
    Prev
    Next
    INDEX
    Explanations

    parenting and family

    np_max-act · gemini-2.0-flash

    The neuron lights up on caring, supportive or emotional language—words expressing love, empathy, advice or encouragement.

    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
    combe
    -0.07
     Valve
    -0.07
     кор
    -0.07
    orton
    -0.06
     bonds
    -0.06
    能力
    -0.06
     Uncle
    -0.06
     oats
    -0.06
    _ALIGN
    -0.06
     Lod
    -0.06
    POSITIVE LOGITS
    .spark
    0.06
     accompanying
    0.06
    _ghost
    0.06
     مس
    0.06
    ifo
    0.06
    ถม
    0.06
    .Scan
    0.06
    Receipt
    0.06
     querying
    0.06
    ोख
    0.06
    Activations Density 0.101%

    No Known Activations