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. 80987
    Prev
    Next
    INDEX
    Explanations

    Units of measure

    np_max-act · gemini-2.0-flash

    keywords related to medical research on vein grafts and their biochemical responses.

    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
    opa
    -0.07
    fds
    -0.07
    (flow
    -0.07
     gebru
    -0.07
     LOOP
    -0.07
    .cons
    -0.07
    arta
    -0.07
     towel
    -0.07
     fore
    -0.07
     guy
    -0.07
    POSITIVE LOGITS
    .web
    0.06
    .badlogic
    0.06
     unavoidable
    0.06
    日本
    0.06
    ]")↵
    0.06
    `,↵
    0.06
    _he
    0.06
     billions
    0.05
     (↵
    0.05
    ")↵
    0.05
    Activations Density 0.009%

    No Known Activations