© 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. 77653
    Prev
    Next
    INDEX
    Explanations

    temperature

    np_max-act · gemini-2.0-flash
    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
     inte
    -0.07
    igure
    -0.06
    �
    -0.06
    kf
    -0.06
     Iz
    -0.06
    Gs
    -0.06
    oice
    -0.06
     Од
    -0.06
    ùng
    -0.06
    itates
    -0.06
    POSITIVE LOGITS
     Celsius
    0.10
    ahrenheit
    0.09
     Fahrenheit
    0.08
    elsius
    0.07
     thermometer
    0.07
     oppressive
    0.07
    laması
    0.06
     ferment
    0.06
    (Environment
    0.06
    _HERSHEY
    0.06
    Activations Density 0.004%

    No Known Activations