Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 129432
    Prev
    Next
    INDEX
    Explanations

    accordion

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the term “accordion” (in any casing or slight variation) in the text.

    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
    ΟΛ
    -0.07
     �
    -0.07
     righteousness
    -0.07
    sqrt
    -0.06
     чого
    -0.06
     невозможно
    -0.06
    ("");↵
    -0.06
    荒
    -0.06
     هنگام
    -0.06
     nast
    -0.06
    POSITIVE LOGITS
    accordion
    0.07
    ǐ
    0.07
     structures
    0.07
    ,M
    0.07
    _colour
    0.06
    Accordion
    0.06
     inflater
    0.06
     unsur
    0.06
    .animation
    0.06
     bumper
    0.06
    Activations Density 0.006%

    No Known Activations