© 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. 91993
    Prev
    Next
    INDEX
    Explanations

    Oxidation and glycation

    np_max-act · gemini-2.0-flash

    The neuron responds to terms describing chemical oxidation or glycation modifications of biomolecules (e.g. protein oxidation, advanced glycation end products, cross‐links).

    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
    (keyword
    -0.06
    /update
    -0.06
    CAT
    -0.06
     height
    -0.06
    Compute
    -0.06
    Mapper
    -0.06
    _near
    -0.06
    @store
    -0.06
     kinase
    -0.05
    еним
    -0.05
    POSITIVE LOGITS
     жил
    0.08
    ็จพระ
    0.07
     nas
    0.07
     区
    0.07
     rang
    0.07
     eso
    0.07
    ><?=$
    0.07
     vit
    0.07
    getMessage
    0.06
     tanın
    0.06
    Activations Density 0.013%

    No Known Activations