© 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. 28802
    Prev
    Next
    INDEX
    Explanations

    numerical values and parameter definitions in technical contexts

    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
    inning
    -0.07
    680
    -0.06
    ix
    -0.06
    ÑĤÑĢон
    -0.06
    ertainment
    -0.06
    hait
    -0.06
    createForm
    -0.06
    pent
    -0.06
    iste
    -0.06
     Tay
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
    SEQ
    0.07
    Gratis
    0.07
    دÛĮگر
    0.07
    ÑĪÑĥ
    0.06
    torrent
    0.06
    Pts
    0.06
    .scalablytyped
    0.06
     critic
    0.06
     надеж
    0.06
    Activations Density 0.003%

    No Known Activations