© 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. 15-LLAMASCOPE-RES-131K
    11. 88482
    Prev
    Next
    INDEX
    Explanations

    references to computer hardware, specifically related to Mac products

    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
    opp
    -0.09
    jišť
    -0.07
     impe
    -0.07
    flip
    -0.07
     Xperia
    -0.07
    ãĤįãģĨ
    -0.07
    kul
    -0.07
    Dash
    -0.07
    .scalablytyped
    -0.07
     Rover
    -0.06
    POSITIVE LOGITS
    agli
    0.06
     Glass
    0.06
     Fritz
    0.06
     Shack
    0.06
     Cir
    0.06
    922
    0.06
    åªĴ
    0.06
    icio
    0.06
    .Compute
    0.06
     Stanley
    0.06
    Activations Density 0.001%

    No Known Activations