© 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. 124412
    Prev
    Next
    INDEX
    Explanations

    highlights and notable events in community gatherings or celebrations

    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
     gratuiti
    -0.08
    é§
    -0.07
    alars
    -0.07
    inki
    -0.07
    ãģµ
    -0.07
    _RSP
    -0.07
    SupportedContent
    -0.07
    огÑĥ
    -0.07
     guar
    -0.07
    INVAL
    -0.07
    POSITIVE LOGITS
     awards
    0.09
     Awards
    0.09
     award
    0.09
     Award
    0.08
     presentation
    0.07
     (
    0.07
     officially
    0.06
    Award
    0.06
     introduction
    0.06
     indu
    0.06
    Activations Density 0.036%

    No Known Activations