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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 104435
    Prev
    Next
    INDEX
    Explanations

    range of motion

    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
     Το
    -0.06
    _STORAGE
    -0.06
     deneyim
    -0.06
     Kore
    -0.06
     Yong
    -0.06
    .sys
    -0.06
    _HALF
    -0.06
     boy
    -0.06
     boiled
    -0.06
     Provid
    -0.06
    POSITIVE LOGITS
    .XtraBars
    0.07
     aggravated
    0.06
     Mercedes
    0.06
    RGB
    0.06
     gain
    0.06
     press
    0.06
    train
    0.06
    BarButton
    0.06
    _period
    0.06
    -Mobile
    0.06
    Activations Density 0.009%

    No Known Activations