© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 30021
    Prev
    Next
    INDEX
    Explanations

    ui

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cd
    -0.08
    dm
    -0.07
     tm
    -0.07
     Direct
    -0.06
    /M
    -0.06
     Christmas
    -0.06
     "-",
    -0.06
     Protected
    -0.06
     dt
    -0.06
    Detect
    -0.06
    POSITIVE LOGITS
    <double
    0.07
    entina
    0.07
    γα
    0.06
    나
    0.06
    STATE
    0.06
    メージ
    0.06
     قابل
    0.06
    _RUNNING
    0.06
    건
    0.06
     footing
    0.06
    Activations Density 0.023%

    No Known Activations