Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96136
    Prev
    Next
    INDEX
    Explanations

    references to financial metrics and statistics

    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
    nt
    -0.06
    ContentLoaded
    -0.06
    ACING
    -0.06
    OMIC
    -0.06
    ORA
    -0.06
     Moss
    -0.06
    uesta
    -0.06
     Dane
    -0.06
     ming
    -0.06
    ACE
    -0.06
    POSITIVE LOGITS
    ardon
    0.07
    ittest
    0.07
     endwhile
    0.06
    ensex
    0.06
    .habbo
    0.06
    ourcem
    0.06
    ynos
    0.06
    ÚĺÛĮ
    0.06
    doctrine
    0.06
    .LayoutStyle
    0.06
    Activations Density 0.000%

    No Known Activations