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. 3-RESID-POST-AA
    6. 122822
    Prev
    Next
    INDEX
    Explanations

    figure

    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
    .Helper
    -0.07
    	web
    -0.07
     陈
    -0.07
    -off
    -0.07
     �
    -0.06
    ners
    -0.06
     attend
    -0.06
    運
    -0.06
    .Helpers
    -0.06
    nom
    -0.06
    POSITIVE LOGITS
    Fig
    0.16
    figure
    0.15
     Figure
    0.12
    Figure
    0.12
     Fig
    0.11
     FIG
    0.10
     Figures
    0.09
    _inches
    0.08
    _figure
    0.08
    _fig
    0.08
    Activations Density 0.014%

    No Known Activations