© 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. 108036
    Prev
    Next
    INDEX
    Explanations

    references to structured data systems and their components

    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
    reo
    -0.06
    eger
    -0.06
    efeller
    -0.06
    å¯Ŀ
    -0.06
    icum
    -0.06
    ipay
    -0.06
    avad
    -0.06
    dna
    -0.06
    imeter
    -0.05
    調
    -0.05
    POSITIVE LOGITS
    ÐŁÐļ
    0.07
    اÙĦÙī
    0.07
    еко
    0.07
    achuset
    0.06
    è¥
    0.06
    ÙĤÙĪÙĦ
    0.06
    ,↵↵↵↵
    0.06
    çľī
    0.06
    ovacÃŃ
    0.06
     поÑģк
    0.06
    Activations Density 0.006%

    No Known Activations