© 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 EvalsExportsinterp-engineNEWAPI 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. 15-RESID-POST-AA
    11. 86758
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    a domain/discipline marker: it fires on institutional, regional, or scientific descriptors (e.g., "international," "clinical," "federal," "interstellar," "neonatal") that signal a formal academic or technical context.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Namen
    -0.07
    _TIMEOUT
    -0.06
     credentials
    -0.06
    ,the
    -0.06
    ователь
    -0.06
     Honestly
    -0.06
     GDP
    -0.06
    101
    -0.06
    	inst
    -0.06
    006
    -0.05
    POSITIVE LOGITS
     )
↵
    0.07
    }↵↵↵↵↵
    0.06
     состав
    0.06
    .TabPage
    0.06
    =file
    0.06
    .Blue
    0.06
     SEN
    0.06
     ),
↵
    0.06
    .RIGHT
    0.06
     disregard
    0.06
    Activations Density 0.155%

    No Known Activations