© 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. 11-RESID-POST-AA
    6. 124815
    Prev
    Next
    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash

    The neuron detects Spanish quiz question prompts by firing on occurrences of the word “pregunta(s)” and the numeric counts associated with them.

    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
     Crystal
    -0.07
     Swe
    -0.07
     encoding
    -0.07
     prayer
    -0.06
    Cx
    -0.06
    Device
    -0.06
     fluor
    -0.06
     treated
    -0.06
     Exchange
    -0.06
    Crystal
    -0.06
    POSITIVE LOGITS
    ी.
    0.07
    asmine
    0.07
     характ
    0.06
    ợ
    0.06
    ]'↵
    0.06
    973
    0.06
    ]"↵
    0.06
     relentlessly
    0.06
     remaining
    0.06
     thiệu
    0.06
    Activations Density 0.028%

    No Known Activations