© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62137
    Prev
    Next
    INDEX
    Explanations

    words related to links or references

    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
     /*#__
    -0.07
    unter
    -0.06
    gi
    -0.06
    еж
    -0.06
    /layouts
    -0.06
    odor
    -0.06
    untas
    -0.06
    ãĥ«ãĥĪ
    -0.06
    ancell
    -0.06
    PLETED
    -0.06
    POSITIVE LOGITS
    .documentation
    0.07
     showc
    0.07
    misc
    0.07
    اÙĪØ±ÛĮ
    0.07
    ikut
    0.07
    ç´
    0.07
    rysler
    0.07
     extern
    0.06
    GPC
    0.06
    IFEST
    0.06
    Activations Density 0.002%

    No Known Activations