© 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. 93693
    Prev
    Next
    INDEX
    Explanations

    references to Samsung Galaxy products

    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
    bef
    -0.07
    ulen
    -0.06
    uding
    -0.06
    ANNEL
    -0.06
    件
    -0.06
     dried
    -0.06
     int
    -0.06
     flexGrow
    -0.06
    yleft
    -0.06
    western
    -0.06
    POSITIVE LOGITS
    ominator
    0.07
    -series
    0.07
     series
    0.07
     nieu
    0.07
    arer
    0.07
     Huff
    0.06
     serie
    0.06
    isms
    0.06
    'gc
    0.06
    CAF
    0.06
    Activations Density 0.015%

    No Known Activations