© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60427
    Prev
    Next
    INDEX
    Explanations

    complex filtering and prediction techniques in analytical 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
    604
    -0.07
    EntryPoint
    -0.07
    xea
    -0.07
    ÐĶÐļ
    -0.07
    Äįe
    -0.07
    _marshall
    -0.06
    bek
    -0.06
    appa
    -0.06
    RICT
    -0.06
    603
    -0.06
    POSITIVE LOGITS
     multiple
    0.10
    multiple
    0.09
     multi
    0.08
     different
    0.08
    Multiple
    0.07
     Multiple
    0.07
    multi
    0.07
     special
    0.07
     addCriterion
    0.07
     combinations
    0.06
    Activations Density 0.091%

    No Known Activations