Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 36093
    Prev
    Next
    INDEX
    Explanations

    haptic

    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
     predictors
    -0.06
    内部
    -0.06
    ellites
    -0.06
     qa
    -0.06
    hecy
    -0.06
     Disease
    -0.06
    onds
    -0.06
    鮮
    -0.06
    PRI
    -0.06
     tumor
    -0.06
    POSITIVE LOGITS
    ///
    ↵
    0.07
     tactile
    0.07
     allot
    0.07
    toList
    0.06
    addWidget
    0.06
    ,st
    0.06
     baise
    0.06
     тан
    0.06
    agements
    0.06
     way
    0.06
    Activations Density 0.005%

    No Known Activations