Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 85618
    Prev
    Next
    INDEX
    Explanations

    language and grammar

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive adjectives (words used to characterize or detail things).

    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
     انج
    -0.06
     cocktail
    -0.06
     ×
    -0.06
    _star
    -0.06
     сад
    -0.06
    edula
    -0.06
     четы
    -0.06
    Note
    -0.06
    .bel
    -0.06
    anno
    -0.06
    POSITIVE LOGITS
     numa
    0.07
    "..
    0.07
     usable
    0.06
    -context
    0.06
    KER
    0.06
    raisal
    0.06
     kombin
    0.06
    args
    0.06
     Pacers
    0.06
    خص
    0.06
    Activations Density 0.057%

    No Known Activations