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. 84166
    Prev
    Next
    INDEX
    Explanations

    nazis/hitler

    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
    ()↵↵↵↵
    -0.06
    908
    -0.06
    fp
    -0.06
    addContainerGap
    -0.06
    створ
    -0.06
    레
    -0.06
    ư
    -0.06
    「你
    -0.06
     USERS
    -0.06
    ")]
    ↵
    -0.06
    POSITIVE LOGITS
     hoş
    0.07
    glob
    0.07
    ớm
    0.07
    ji
    0.07
    Moving
    0.06
     tiers
    0.06
     smoothed
    0.06
    -away
    0.06
     consect
    0.06
     extends
    0.06
    Activations Density 0.011%

    No Known Activations