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. 15-RESID-POST-AA
    6. 1271
    Prev
    Next
    INDEX
    Explanations

    it

    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
     Cbd
    -0.07
    Texture
    -0.07
    -inst
    -0.07
    ูง
    -0.06
    페
    -0.06
    \Form
    -0.06
     Enumeration
    -0.06
    ователь
    -0.06
    adí
    -0.06
     ді
    -0.06
    POSITIVE LOGITS
    NavController
    0.07
     contends
    0.06
    (...)↵
    0.06
    єю
    0.06
    	LOGGER
    0.06
    Ess
    0.06
     Eb
    0.06
    ,date
    0.06
    (QL
    0.06
    _armor
    0.06
    Activations Density 0.000%

    No Known Activations