© 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. 57485
    Prev
    Next
    INDEX
    Explanations

    a variety of past actions and states related to development and implementation processes

    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
    ewis
    -0.08
     proport
    -0.08
    antity
    -0.08
    roje
    -0.08
    .Magenta
    -0.08
    लत
    -0.08
    asje
    -0.07
    alue
    -0.07
    еÑĩ
    -0.07
    ktor
    -0.07
    POSITIVE LOGITS
     yesterday
    0.13
     last
    0.12
     originally
    0.12
     recently
    0.11
     earlier
    0.10
    /is
    0.09
     Originally
    0.08
     during
    0.08
    nt
    0.07
     initially
    0.07
    Activations Density 0.121%

    No Known Activations