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. 87114
    Prev
    Next
    INDEX
    Explanations

    기

    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
     Trent
    -0.07
     Conn
    -0.07
    Even
    -0.07
     Stout
    -0.07
    Com
    -0.07
    UiThread
    -0.06
    								
    -0.06
    Formatted
    -0.06
    .RED
    -0.06
     naprost
    -0.06
    POSITIVE LOGITS
    하기
    0.10
     기
    0.09
    기
    0.09
    하지
    0.08
    ANGES
    0.08
    基
    0.08
    보기
    0.08
    基于
    0.07
     userData
    0.07
     Psycho
    0.07
    Activations Density 0.008%

    No Known Activations