© 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. 15-LLAMASCOPE-RES-131K
    11. 27103
    Prev
    Next
    INDEX
    Explanations

    computer programming or coding structures, particularly related to variables and functions

    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
    lessly
    -0.07
    ment
    -0.06
     herself
    -0.06
    exus
    -0.06
    orent
    -0.06
    icher
    -0.06
    umper
    -0.06
    abal
    -0.06
    wen
    -0.06
    so
    -0.06
    POSITIVE LOGITS
    кÑĢаÑĹ
    0.07
    ÑĥлÑİ
    0.07
    elts
    0.07
     nét
    0.06
    ëıħ
    0.06
    جÙħ
    0.06
    anco
    0.06
     olmak
    0.06
    upiter
    0.06
    ë¡ľëĤĺ
    0.06
    Activations Density 0.152%

    No Known Activations