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. 104317
    Prev
    Next
    INDEX
    Explanations

    manuscripts

    np_max-act · gemini-2.0-flash

    academic and research-related terminology associated with health sciences and training programs.

    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
    АН
    -0.06
     Bac
    -0.06
    lide
    -0.06
     професси
    -0.06
     turnout
    -0.06
    <<"
    -0.06
     tilt
    -0.06
     gluten
    -0.06
    sprintf
    -0.06
    ()]
    -0.06
    POSITIVE LOGITS
     таке
    0.07
     WITHOUT
    0.07
     nghị
    0.07
     denies
    0.07
    enny
    0.07
     TABLE
    0.07
    /vue
    0.06
    fillable
    0.06
    .microsoft
    0.06
    ốt
    0.06
    Activations Density 0.016%

    No Known Activations