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. 81175
    Prev
    Next
    INDEX
    Explanations

    Fictional narratives

    np_max-act · gemini-2.0-flash

    character descriptions that emphasize physical traits and ethnic backgrounds.

    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
     oznám
    -0.07
     construed
    -0.06
    �
    -0.06
     ]↵
    -0.06
     describe
    -0.06
    .new
    -0.06
    _wave
    -0.06
     currents
    -0.06
     bm
    -0.06
    modes
    -0.06
    POSITIVE LOGITS
    entreprise
    0.07
    hesive
    0.06
    <Renderer
    0.06
     Olymp
    0.06
     quarterback
    0.06
    nd
    0.06
     MUCH
    0.06
     RE
    0.06
    Drv
    0.06
    ressing
    0.06
    Activations Density 0.032%

    No Known Activations