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. 86058
    Prev
    Next
    INDEX
    Explanations

    alpha-helices

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of alpha-helical structure—particularly references to alpha-helix periodicity, turns, or coiled-coil helical segments in proteins.

    oai_token-act-pair · o4-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
     रखन
    -0.08
    _PKG
    -0.07
     strings
    -0.07
    efa
    -0.07
    .functional
    -0.06
    ậu
    -0.06
    ugu
    -0.06
    �
    -0.06
     bouquet
    -0.06
    AttributedString
    -0.06
    POSITIVE LOGITS
     Gothic
    0.08
    <Field
    0.07
     HIV
    0.07
    Flexible
    0.06
    (rv
    0.06
     MICRO
    0.06
     Hass
    0.06
     straightforward
    0.06
    _Component
    0.06
     зас
    0.06
    Activations Density 0.002%

    No Known Activations