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. 104216
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash

    information related to places and contexts for sexual activities.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    win
    -0.07
    _points
    -0.07
    Tasks
    -0.07
    WIN
    -0.07
     이어
    -0.06
     ورد
    -0.06
     talks
    -0.06
     interval
    -0.06
     light
    -0.06
     млн
    -0.06
    POSITIVE LOGITS
    oce
    0.07
    const
    0.07
    **(
    0.07
     rural
    0.06
     moderators
    0.06
     preseason
    0.06
     graves
    0.06
    inecraft
    0.06
    ierarchy
    0.06
    --){↵
    0.06
    Activations Density 0.048%

    No Known Activations