© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110324
    Prev
    Next
    INDEX
    Explanations

    novel

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of words signaling novelty (e.g. “novel” or “new”) in scientific descriptions.

    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
    arb
    -0.07
     LGBT
    -0.07
    منی
    -0.06
    _super
    -0.06
     mph
    -0.06
    Bad
    -0.06
    Harry
    -0.06
     gang
    -0.06
     případech
    -0.06
     glare
    -0.06
    POSITIVE LOGITS
    isEmpty
    0.07
     Craigslist
    0.06
     teas
    0.06
    .Var
    0.06
    /testify
    0.06
     steward
    0.05
    Disclosure
    0.05
    ResourceManager
    0.05
     капіт
    0.05
    #####
    0.05
    Activations Density 0.012%

    No Known Activations