© 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. 125264
    Prev
    Next
    INDEX
    Explanations

    phenotype

    np_max-act · gemini-2.0-flash

    The neuron is activated by specialized scientific terminology—especially multi‐syllabic tokens related to phenotypic traits, plasticity, adaptation, and evolutionary genetics.

    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
    turned
    -0.07
     presentations
    -0.07
     culmination
    -0.07
    _CLEAR
    -0.06
    	request
    -0.06
     karış
    -0.06
    reading
    -0.06
     HttpStatusCode
    -0.06
     CASCADE
    -0.06
    Hash
    -0.06
    POSITIVE LOGITS
    _lhs
    0.08
     Nev
    0.07
    ществ
    0.06
    бора
    0.06
     Loans
    0.06
    subset
    0.06
     zaměř
    0.06
    asy
    0.06
     Ngọc
    0.06
     booty
    0.06
    Activations Density 0.011%

    No Known Activations