© 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. 125182
    Prev
    Next
    INDEX
    Explanations

    toxic

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of toxicity (e.g., “toxic,” “toxicity,” or “less toxic”) in treatment‐related contexts.

    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
    buah
    -0.07
    幾
    -0.06
    rw
    -0.06
     оказ
    -0.06
     sức
    -0.06
     upt
    -0.06
    igung
    -0.06
     одерж
    -0.06
     Crack
    -0.06
    approve
    -0.06
    POSITIVE LOGITS
     god
    0.06
    							 
    0.06
     intrusion
    0.06
    Carrier
    0.06
     Magic
    0.06
    ứa
    0.06
    XB
    0.06
    IRC
    0.06
     XII
    0.06
     boyfriend
    0.06
    Activations Density 0.017%

    No Known Activations