© 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. 65571
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    the main thing this neuron does is find numeric tokens, especially floating-point decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    narratives centered around crime and investigation.

    oai_token-act-pair · gpt-4o-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
    956
    -0.07
    935
    -0.07
    imes
    -0.07
    gMaps
    -0.06
     shock
    -0.06
    prü
    -0.06
    892
    -0.06
    .st
    -0.06
    946
    -0.06
    ช
    -0.06
    POSITIVE LOGITS
                                    
    0.07
     istediğiniz
    0.07
     newPassword
    0.06
     куст
    0.06
     initialize
    0.06
    appearance
    0.06
     🙂
    0.06
    igua
    0.06
    자기
    0.06
    =target
    0.06
    Activations Density 0.107%

    No Known Activations