© 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. 15-LLAMASCOPE-RES-131K
    11. 87330
    Prev
    Next
    INDEX
    Explanations

    technical specifications and structural elements related to systems or concepts

    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
    оÑĤÑĢеб
    -0.08
    áš
    -0.07
    .ant
    -0.07
    omik
    -0.07
     endregion
    -0.06
    ürn
    -0.06
    esel
    -0.06
    .lu
    -0.06
    ÑģÑıг
    -0.06
    íĥķ
    -0.06
    POSITIVE LOGITS
    primary
    0.08
     central
    0.07
     designated
    0.07
     Primary
    0.07
    /main
    0.07
     Sink
    0.07
     primary
    0.06
     role
    0.06
    Primary
    0.06
     leader
    0.06
    Activations Density 0.039%

    No Known Activations