© 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. 87046
    Prev
    Next
    INDEX
    Explanations

    references to legal postings and dates

    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
    warz
    -0.06
    leich
    -0.06
    631
    -0.06
    _increment
    -0.06
    ÇIJ
    -0.06
    inho
    -0.06
    isté
    -0.06
     whistle
    -0.05
    avs
    -0.05
     nest
    -0.05
    POSITIVE LOGITS
    ALLE
    0.09
     ============================================================================↵
    0.07
    ERVE
    0.07
    _nh
    0.07
    imizer
    0.06
     é©
    0.06
    lun
    0.06
    ÏĨÎŃ
    0.06
    ÙĪÙĦÙĬÙĪ
    0.06
     Vinci
    0.06
    Activations Density 0.003%

    No Known Activations