© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84497
    Prev
    Next
    INDEX
    Explanations

    references to data structure or manipulation in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ạt
    -0.07
    iske
    -0.07
    arness
    -0.07
    NaN
    -0.07
    éru
    -0.07
    dek
    -0.07
    ÑĢиÑĤи
    -0.07
    HeaderValue
    -0.07
    iedy
    -0.07
    iken
    -0.07
    POSITIVE LOGITS
     axis
    0.07
     dimensions
    0.07
     Axis
    0.07
    elper
    0.07
    eld
    0.06
    axis
    0.06
     sw
    0.06
     Bush
    0.06
    ìĥ
    0.06
     Mushroom
    0.06
    Activations Density 0.002%

    No Known Activations