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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 38066
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    formal announcements of leadership changes within organizations.

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

    The neuron responds to sentence-ending punctuation (specifically periods), marking sentence boundaries.

    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
    빠
    -0.08
    BERT
    -0.07
    ากล
    -0.06
    ethyl
    -0.06
    (currentUser
    -0.06
    очку
    -0.06
     finding
    -0.06
    Fi
    -0.06
    ');
↵
↵
    -0.06
    辛
    -0.06
    POSITIVE LOGITS
    	glBind
    0.06
    ."
    0.06
     exports
    0.06
    !"
    0.06
    .'
    0.06
    .(*
    0.06
    _lost
    0.06
      
    0.06
    	Use
    0.06
    '
    0.06
    Activations Density 0.351%

    No Known Activations