© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 546
    Prev
    Next
    INDEX
    Explanations

    genomics research papers

    np_max-act · gemini-2.0-flash

    This neuron responds most strongly to common high-frequency function words (e.g. “the,” “of,” “in”) characteristic of formal scientific writing.

    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
    .currentTime
    -0.06
    validator
    -0.06
    OpenGL
    -0.06
    Dropdown
    -0.06
     інтерес
    -0.06
    precision
    -0.06
    ैर
    -0.06
    .purchase
    -0.06
     conduct
    -0.06
    probability
    -0.06
    POSITIVE LOGITS
    .j
    0.06
    :#
    0.06
    스템
    0.06
     Volk
    0.06
     sik
    0.06
    /target
    0.06
     Sender
    0.06
     judging
    0.06
     Installer
    0.06
    }
    0.06
    Activations Density 0.026%

    No Known Activations