© 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
    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. 29733
    Prev
    Next
    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash

    The neuron activates on the structural prompt and tool‐invocation tokens—i.e. the system/user instruction scaffolding rather than content words.

    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
    θεν
    -0.07
    _UFunction
    -0.06
     üzer
    -0.06
    amaz
    -0.06
    .Username
    -0.06
    �
    -0.06
     oma
    -0.06
    _>
    -0.06
     unnoticed
    -0.06
    .sendMessage
    -0.05
    POSITIVE LOGITS
    вают
    0.07
     Senator
    0.07
     confusing
    0.06
    国际
    0.06
     UIAlert
    0.06
    _gpio
    0.06
     рух
    0.06
    uddle
    0.06
    Aceptar
    0.06
    言わ
    0.06
    Activations Density 0.009%

    No Known Activations