© 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. 84252
    Prev
    Next
    INDEX
    Explanations

    technical specifications and component information related to technology

    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
    Backing
    -0.07
    ye
    -0.06
    over
    -0.06
     backing
    -0.06
    adle
    -0.06
     mo
    -0.06
     Vehicles
    -0.06
     RTP
    -0.06
    uggle
    -0.06
    .toCharArray
    -0.06
    POSITIVE LOGITS
    avy
    0.07
     ì¶ľìĭľ
    0.07
    early
    0.06
    marketing
    0.06
     Release
    0.06
    iena
    0.06
    akra
    0.06
    ivec
    0.06
     Wikispecies
    0.06
     ëĭ¹ìĭľ
    0.06
    Activations Density 0.001%

    No Known Activations