© 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. 40148
    Prev
    Next
    INDEX
    Explanations

    references to a specific type of rest or restoration

    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
    led
    -0.08
    aison
    -0.07
    estar
    -0.07
    eldorf
    -0.07
    ÈĻi
    -0.07
    anders
    -0.07
    osen
    -0.07
    çİĩ
    -0.07
    keit
    -0.07
    etry
    -0.07
    POSITIVE LOGITS
    orative
    0.11
    aurants
    0.09
    repo
    0.09
    ful
    0.09
    atement
    0.08
    itution
    0.08
    (rest
    0.07
    .Rest
    0.07
    oration
    0.07
     rest
    0.07
    Activations Density 0.017%

    No Known Activations