© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82671
    Prev
    Next
    INDEX
    Explanations

    references to context management in programming

    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
    erdem
    -0.08
    र
    -0.08
    ERIC
    -0.08
    thers
    -0.08
    erable
    -0.08
    ideshow
    -0.08
    achi
    -0.07
    ager
    -0.07
    igel
    -0.07
    eric
    -0.07
    POSITIVE LOGITS
    ually
    0.16
    ual
    0.13
    uality
    0.11
    less
    0.09
    ively
    0.08
    UAL
    0.08
    ted
    0.08
    s
    0.07
    ally
    0.07
    MenuStrip
    0.07
    Activations Density 0.024%

    No Known Activations