© 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. 107454
    Prev
    Next
    INDEX
    Explanations

    units of measurement and data transfer rates

    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
     Shame
    -0.06
    kees
    -0.06
    IVO
    -0.06
     tele
    -0.06
    ikan
    -0.06
    evi
    -0.06
    ATCH
    -0.06
     teleport
    -0.05
    ACEMENT
    -0.05
    chant
    -0.05
    POSITIVE LOGITS
    ÅĻe
    0.07
    utenberg
    0.07
    iones
    0.07
    era
    0.07
    ishi
    0.07
    ibar
    0.07
    Assignable
    0.07
    çİĽ
    0.06
    Barrier
    0.06
     ÑĢÑĥб
    0.06
    Activations Density 0.020%

    No Known Activations