© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126187
    Prev
    Next
    INDEX
    Explanations

    protein

    np_max-act · gemini-2.0-flash

    The neuron consistently activates on occurrences of the word “protein” (including its variants and compounds), marking mentions of 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
    (SDL
    -0.07
    	O
    -0.06
     jack
    -0.06
     IGN
    -0.06
    ingleton
    -0.06
     errs
    -0.06
     Insights
    -0.06
    yahoo
    -0.06
    KHR
    -0.06
     broth
    -0.06
    POSITIVE LOGITS
     aging
    0.06
    anti
    0.06
    맥
    0.06
     운
    0.06
    /content
    0.06
    .textView
    0.06
    _half
    0.05
    pis
    0.05
     آموز
    0.05
    male
    0.05
    Activations Density 0.013%

    No Known Activations