© 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. 109456
    Prev
    Next
    INDEX
    Explanations

    describes what is special

    np_max-act · gemini-2.0-flash

    This neuron activates on phrasing that highlights or questions an item’s distinguishing or unique features (e.g. “what makes… different,” “unique,” “special,” “sets… apart”).

    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
    ycler
    -0.07
    世
    -0.07
    name
    -0.06
     Flu
    -0.06
    :(
    -0.06
     Stroke
    -0.06
    .time
    -0.06
     filePath
    -0.06
    mobile
    -0.06
     Mary
    -0.06
    POSITIVE LOGITS
     陳
    0.07
     Oyun
    0.07
    지는
    0.07
     Batter
    0.06
     AssemblyTitle
    0.06
     Existing
    0.06
    ो,
    0.06
    готов
    0.06
    ős
    0.06
    /spec
    0.06
    Activations Density 0.033%

    No Known Activations