© 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 EvalsExportsinterp-engineNEWAPI 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. 79731
    Prev
    Next
    INDEX
    Explanations

    references to points in a scoring or competitive context

    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
    PHA
    -0.09
    PF
    -0.07
    jang
    -0.07
     ThÆ°Æ¡ng
    -0.07
    lund
    -0.07
    elige
    -0.07
    çŁ¢
    -0.07
    .opensource
    -0.07
    atsu
    -0.07
    uyla
    -0.07
    POSITIVE LOGITS
     points
    0.07
     revenue
    0.06
    oleon
    0.06
     gained
    0.06
     vit
    0.06
     profits
    0.06
    vs
    0.06
    eyn
    0.06
     result
    0.06
     DESC
    0.05
    Activations Density 0.013%

    No Known Activations