© 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. 17-LLAMASCOPE-RES-131K
    6. 106879
    Prev
    Next
    INDEX
    Explanations

    references to tables and their arrangements

    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
    uml
    -0.08
     Boiler
    -0.07
    zh
    -0.07
     trom
    -0.07
     Peer
    -0.06
    ÑģÑĭлки
    -0.06
     Scaffold
    -0.06
     Trom
    -0.06
     Boot
    -0.06
    ronics
    -0.06
    POSITIVE LOGITS
    /table
    0.08
     table
    0.08
    .table
    0.07
    rase
    0.07
     surface
    0.07
    pread
    0.07
    /Table
    0.07
    table
    0.07
    (table
    0.06
    ellite
    0.06
    Activations Density 0.018%

    No Known Activations