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. 19-RESID-POST-AA
    6. 127607
    Prev
    Next
    INDEX
    Explanations

    HTML code

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    registro
    -0.06
    Round
    -0.06
    compiled
    -0.06
     //-
    -0.06
    	protected
    -0.06
    )]);↵
    -0.06
     свер
    -0.06
    裡
    -0.06
    Enough
    -0.05
     sık
    -0.05
    POSITIVE LOGITS
    NU
    0.07
    ++,
    0.07
     pokus
    0.07
    .Bad
    0.06
    eeper
    0.06
     implicitly
    0.06
     Included
    0.06
    aşa
    0.06
    ondheim
    0.06
    _helpers
    0.06
    Activations Density 0.008%

    No Known Activations