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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 60911
    Prev
    Next
    INDEX
    Explanations

    references to specific car models and their features

    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
    wear
    -0.06
    stral
    -0.06
    lon
    -0.06
    .exports
    -0.06
    .scalablytyped
    -0.06
    ationToken
    -0.06
    theid
    -0.06
    ä»¶
    -0.06
     OMAP
    -0.06
     itemprop
    -0.06
    POSITIVE LOGITS
    apos
    0.07
    arts
    0.07
    _mk
    0.07
     serie
    0.07
     nackte
    0.07
     series
    0.06
     Äijá»Ŀi
    0.06
     phiên
    0.06
     outf
    0.06
    _STANDARD
    0.06
    Activations Density 0.019%

    No Known Activations