© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements or capacities

    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
     Rate
    -0.07
     rate
    -0.06
     coalition
    -0.06
     tu
    -0.05
     RATE
    -0.05
    -rate
    -0.05
     Mode
    -0.05
    _rate
    -0.05
    åŀĤ
    -0.05
     pass
    -0.05
    POSITIVE LOGITS
     sizes
    0.19
     size
    0.18
    size
    0.16
    sizes
    0.16
     sized
    0.16
    -size
    0.16
     Size
    0.16
     larger
    0.16
    _sizes
    0.15
    -sized
    0.15
    Activations Density 0.172%

    No Known Activations