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. 3-RESID-POST-AA
    6. 95053
    Prev
    Next
    INDEX
    Explanations

    energy

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ベ
    -0.07
    (Stack
    -0.06
     Administrator
    -0.06
     awkward
    -0.06
     winds
    -0.06
    .fail
    -0.06
     Wilhelm
    -0.06
     [`
    -0.06
     cowork
    -0.05
    /web
    -0.05
    POSITIVE LOGITS
     energy
    0.11
     Energy
    0.10
    energy
    0.07
     друж
    0.07
    Energy
    0.07
    rej
    0.07
    \xa
    0.07
     Energ
    0.07
    .panelControl
    0.07
    "';↵
    0.07
    Activations Density 0.016%

    No Known Activations