© 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. 15-RESID-POST-AA
    6. 92766
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    chat-format structural markers and control tokens that denote message boundaries or headers.

    oai_token-act-pair · gpt-5Triggered by @vetterc0

    structural formatting and chat/markup delimiters, such as headers, separators, and list/section markers, rather than content words.

    oai_token-act-pair · gpt-5Triggered 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
    	stack
    -0.07
    .println
    -0.07
    vable
    -0.06
     dracon
    -0.06
    330
    -0.06
    ialized
    -0.06
    olicy
    -0.06
     countries
    -0.06
     decoder
    -0.06
    θο
    -0.06
    POSITIVE LOGITS
    clip
    0.07
     boutique
    0.06
     Он
    0.06
    Он
    0.06
    tile
    0.06
    ете
    0.06
    -prepend
    0.06
    charger
    0.06
     pimp
    0.06
     FormControl
    0.06
    Activations Density 0.265%

    No Known Activations