© 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. 78139
    Prev
    Next
    INDEX
    Explanations

    numerical data and references related to scientific studies

    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
     Clyde
    -0.06
    tvrt
    -0.06
    anni
    -0.06
     retrospect
    -0.06
    gres
    -0.05
     Dis
    -0.05
    æİĴ
    -0.05
     Pey
    -0.05
     Well
    -0.05
     вин
    -0.05
    POSITIVE LOGITS
    .signature
    0.07
    ylim
    0.07
    dens
    0.07
    ãĤ·ãĥ¼
    0.07
    .matmul
    0.07
    etine
    0.07
    hire
    0.07
    ondheim
    0.07
    amous
    0.07
    ãĥ¼ãĥij
    0.07
    Activations Density 0.006%

    No Known Activations