© 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. 15527
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and other textual delimiters in the document

    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
     s
    -0.07
     sp
    -0.06
     ev
    -0.06
     j
    -0.06
     just
    -0.06
     al
    -0.06
     the
    -0.06
    ↵
    -0.06
     ch
    -0.06
     van
    -0.06
    POSITIVE LOGITS
    buah
    0.09
     meisje
    0.08
     ÎĶE
    0.08
    âĹİ
    0.08
     vÃŃdeo
    0.08
     dikke
    0.08
     tiener
    0.08
    EDGE
    0.08
    vá
    0.08
    isure
    0.07
    Activations Density 0.039%

    No Known Activations