© 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. 130645
    Prev
    Next
    INDEX
    Explanations

    references to influential works and their impacts

    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
     outnumber
    -0.07
     именно
    -0.06
    Exactly
    -0.06
    è¤
    -0.06
    AllowAnonymous
    -0.06
     Only
    -0.06
     вÑģего
    -0.06
     ONLY
    -0.06
     exactly
    -0.06
    ONLY
    -0.06
    POSITIVE LOGITS
     another
    0.12
    another
    0.10
    Another
    0.08
     Another
    0.08
     possibilities
    0.08
     otra
    0.07
    åı¦
    0.07
    haps
    0.07
     important
    0.07
    ucht
    0.07
    Activations Density 0.039%

    No Known Activations