© 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. 15-LLAMASCOPE-RES-131K
    11. 90150
    Prev
    Next
    INDEX
    Explanations

    references to schema and schema-related concepts in data management

    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
    allo
    -0.07
    aches
    -0.07
    geh
    -0.07
    juven
    -0.06
    berry
    -0.06
    alez
    -0.06
    ties
    -0.06
     lis
    -0.06
    ÌĢ
    -0.06
    uo
    -0.06
    POSITIVE LOGITS
    yntax
    0.08
    forth
    0.08
    uffman
    0.07
    ierung
    0.07
    ../../../
    0.07
    /DTD
    0.07
    ToFit
    0.07
    inaire
    0.07
    otland
    0.07
    mall
    0.07
    Activations Density 0.007%

    No Known Activations