Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 87117
    Prev
    Next
    INDEX
    Explanations

    emojis

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ống
    -0.07
    irts
    -0.06
    ि�
    -0.06
     visions
    -0.06
     lines
    -0.06
     TRACK
    -0.06
    "=>
    -0.06
    илися
    -0.06
    [..
    -0.06
    Quality
    -0.06
    POSITIVE LOGITS
     viv
    0.07
    =re
    0.06
    *******************************************************************************/↵
    0.06
    Dem
    0.06
     це
    0.06
     Phú
    0.06
    esper
    0.06
     optim
    0.06
    дать
    0.06
    llu
    0.06
    Activations Density 0.005%

    No Known Activations