© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 91397
    Prev
    Next
    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    content related to financial trading practices and tools.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects liability-disclaimer language, particularly phrases saying “not responsible for any…” or similar statements of non-responsibility.

    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
    Requirements
    -0.08
     Harvard
    -0.07
     питания
    -0.06
     burning
    -0.06
    .Pass
    -0.06
     ochran
    -0.06
     bearer
    -0.06
    .Write
    -0.06
     Schneider
    -0.06
     Raf
    -0.06
    POSITIVE LOGITS
    .emplace
    0.06
    �
    0.06
    _ACTION
    0.06
    __↵
    0.06
     Στο
    0.06
    __(*
    0.06
                                    
    0.06
    implode
    0.06
    -‐
    0.06
    <?↵
    0.06
    Activations Density 0.005%

    No Known Activations