© 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. 106154
    Prev
    Next
    INDEX
    Explanations

    financial forecasts and performance metrics

    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
    ov
    -0.06
    zer
    -0.06
     Royal
    -0.06
    Ny
    -0.06
    STA
    -0.06
     Ness
    -0.06
    ì¹´ì§Ģëħ¸
    -0.06
    por
    -0.06
    ogg
    -0.06
    bet
    -0.06
    POSITIVE LOGITS
     expectations
    0.07
     expectation
    0.07
    clusions
    0.06
     sight
    0.06
    jÄĻ
    0.06
    лÑĸн
    0.06
    criptions
    0.06
    357
    0.06
     revis
    0.06
    dbl
    0.06
    Activations Density 0.004%

    No Known Activations