© 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. 106346
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements commonly associated with code documentation

    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
    nger
    -0.07
    rench
    -0.06
    agr
    -0.06
    ela
    -0.05
    bor
    -0.05
     pointer
    -0.05
     McCart
    -0.05
    á»ı
    -0.05
    radi
    -0.05
     Sad
    -0.05
    POSITIVE LOGITS
    SpaceItem
    0.08
    åıĶ
    0.08
    _DECLARE
    0.07
     ydk
    0.07
    legs
    0.07
     fitte
    0.07
    .spi
    0.07
    usra
    0.07
    LEAN
    0.06
    insk
    0.06
    Activations Density 0.005%

    No Known Activations