© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118580
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating significant or notable changes and achievements

    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
    oldem
    -0.07
     Maurice
    -0.07
    .lu
    -0.06
     nét
    -0.06
    _hierarchy
    -0.06
    ãĥ«ãĥī
    -0.06
    .Sdk
    -0.06
     Presents
    -0.06
    olik
    -0.06
     Camb
    -0.06
    POSITIVE LOGITS
     heights
    0.11
     levels
    0.10
     Levels
    0.08
     depths
    0.08
     territory
    0.07
     lengths
    0.07
    levels
    0.07
     conclusions
    0.07
     Heights
    0.07
     speeds
    0.07
    Activations Density 0.027%

    No Known Activations