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. 104291
    Prev
    Next
    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash

    phrases related to community engagement and support 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
     Brazil
    -0.07
     кожи
    -0.07
     станд
    -0.07
     praises
    -0.06
    화를
    -0.06
     builds
    -0.06
     dias
    -0.06
    ्रभ
    -0.06
     effet
    -0.06
    multiline
    -0.06
    POSITIVE LOGITS
     takeover
    0.10
     over
    0.08
     assumed
    0.08
     Nearby
    0.07
    _over
    0.07
    .concurrent
    0.07
    -over
    0.07
    -marker
    0.07
     ATTACK
    0.07
    超
    0.07
    Activations Density 0.004%

    No Known Activations