© 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. 93576
    Prev
    Next
    INDEX
    Explanations

    references to unique or significant items, events, or qualities

    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
    soever
    -0.08
    elic
    -0.07
    presso
    -0.07
    essential
    -0.07
    outh
    -0.06
    plor
    -0.06
    -Pacific
    -0.06
    ed
    -0.06
    gether
    -0.06
    unn
    -0.06
    POSITIVE LOGITS
    ities
    0.11
    ised
    0.11
    -purpose
    0.10
    izations
    0.10
    izing
    0.10
    ity
    0.10
    ties
    0.10
    ise
    0.09
    ize
    0.09
    ising
    0.09
    Activations Density 0.019%

    No Known Activations