© 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. 27283
    Prev
    Next
    INDEX
    Explanations

    elements related to media sources or photography

    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
    浦
    -0.09
    .tex
    -0.07
    ắt
    -0.07
    alion
    -0.07
     addCriterion
    -0.07
    ico
    -0.06
    .cgi
    -0.06
    Ñĥже
    -0.06
    hic
    -0.06
    à¤Ĥप
    -0.06
    POSITIVE LOGITS
     via
    0.08
     License
    0.07
    utterstock
    0.07
     Wikimedia
    0.07
     license
    0.07
     licensors
    0.07
    -license
    0.07
     licens
    0.07
     commons
    0.07
    tle
    0.07
    Activations Density 0.014%

    No Known Activations