© 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. 3-RESID-POST-AA
    11. 122985
    Prev
    Next
    INDEX
    Explanations

    *)

    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
    nee
    -0.07
    Interpolator
    -0.06
    ’,
    -0.06
     Đầu
    -0.06
     wishes
    -0.06
    -Mail
    -0.06
    inate
    -0.06
     زوج
    -0.06
    445
    -0.06
    (WebDriver
    -0.06
    POSITIVE LOGITS
    *)
    0.12
    	MD
    0.08
     *>(
    0.08
    *)(
    0.08
     setText
    0.07
     *)(
    0.07
    _mr
    0.06
    _atoms
    0.06
     غربی
    0.06
    amation
    0.06
    Activations Density 0.002%

    No Known Activations