© 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. 82878
    Prev
    Next
    INDEX
    Explanations

    references to scientific evidence and studies related to health and safety

    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
    kus
    -0.06
    ording
    -0.06
    اذ
    -0.06
     hit
    -0.05
    ween
    -0.05
     Shay
    -0.05
     hardware
    -0.05
    rous
    -0.05
     prime
    -0.05
    ello
    -0.05
    POSITIVE LOGITS
    ertino
    0.09
    support
    0.09
    steder
    0.08
    imson
    0.08
    commission
    0.08
     evidence
    0.08
    NetMessage
    0.08
    arkan
    0.08
    mmc
    0.08
    PTS
    0.07
    Activations Density 0.029%

    No Known Activations