© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12955
    Prev
    Next
    INDEX
    Explanations

    bot

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of chatbots or conversational-AI platforms (e.g. “bot,” “chatbot,” “conversational,” “assistants”).

    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
     panties
    -0.07
    (fi
    -0.06
     FLT
    -0.06
    .ball
    -0.06
     photos
    -0.06
     footage
    -0.06
    armacy
    -0.06
     Cities
    -0.06
     [];↵
    -0.06
    CTS
    -0.06
    POSITIVE LOGITS
     τ
    0.07
     Mon
    0.07
    tsx
    0.06
    VES
    0.06
    �
    0.06
    _SERVER
    0.06
    ServerError
    0.06
    _CO
    0.06
    .token
    0.06
     Qu
    0.06
    Activations Density 0.013%

    No Known Activations