© 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. 29743
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and technical functions

    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
    uci
    -0.06
    chu
    -0.06
    aptop
    -0.06
    ongan
    -0.06
    uc
    -0.06
     Florence
    -0.06
    ufs
    -0.06
    ãĥªãĤ«
    -0.06
     dealt
    -0.06
    loc
    -0.06
    POSITIVE LOGITS
    inverse
    0.08
    ãģ¾ãģ¾
    0.07
    agas
    0.07
     inverse
    0.07
    .inverse
    0.06
    .scalablytyped
    0.06
    agate
    0.06
     easily
    0.06
    è«
    0.06
     Hayward
    0.06
    Activations Density 0.000%

    No Known Activations