© 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. 106705
    Prev
    Next
    INDEX
    Explanations

    terms related to operations and errors in a technical context

    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
    éĤ£ä¸ª
    -0.07
    è¿Ļ个
    -0.07
    cola
    -0.06
    ajan
    -0.06
    971
    -0.06
    ãĥ§
    -0.06
    iggs
    -0.06
    BERS
    -0.06
    andum
    -0.06
    erah
    -0.06
    POSITIVE LOGITS
     các
    0.11
    éĤ£äºĽ
    0.09
     these
    0.08
    è¿ĻäºĽ
    0.08
    äºĽ
    0.08
    "These
    0.08
     những
    0.08
    諸
    0.08
     those
    0.07
    anlar
    0.07
    Activations Density 0.044%

    No Known Activations