© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85371
    Prev
    Next
    INDEX
    Explanations

    references to clinical trials and 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
    /problem
    -0.07
    enth
    -0.07
    ÑģÑı
    -0.07
    ãĥ£
    -0.07
    dra
    -0.07
     Ziel
    -0.06
    اÙĦÙĦÙĩ
    -0.06
    istrovstvÃŃ
    -0.06
    rium
    -0.06
    ohl
    -0.06
    POSITIVE LOGITS
     phase
    0.08
     stage
    0.07
     trial
    0.07
    -stage
    0.07
     trials
    0.07
     studies
    0.06
    s
    0.06
    Safety
    0.06
     proof
    0.06
    gov
    0.06
    Activations Density 0.004%

    No Known Activations