© 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. 15-LLAMASCOPE-RES-131K
    11. 27682
    Prev
    Next
    INDEX
    Explanations

    instances of significant quantitative information or counts related to various subjects

    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
     Sovere
    -0.06
    SSION
    -0.06
    .tbl
    -0.06
    YPES
    -0.06
     bush
    -0.06
    англ
    -0.06
    cestor
    -0.06
    .Dto
    -0.06
     Skeleton
    -0.06
     strip
    -0.05
    POSITIVE LOGITS
    ocha
    0.08
    rement
    0.07
     directly
    0.07
    StringEncoding
    0.07
    InParameter
    0.07
    quee
    0.07
    eday
    0.06
    IsUnicode
    0.06
    mediate
    0.06
    _twitter
    0.06
    Activations Density 0.027%

    No Known Activations