© 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. 3157
    Prev
    Next
    INDEX
    Explanations

    references to historical time periods or durations

    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
    ollar
    -0.07
     Mun
    -0.06
    ãĥ£
    -0.06
    ub
    -0.06
    Untitled
    -0.06
    ager
    -0.06
    express
    -0.06
    utsch
    -0.06
    ella
    -0.06
    aga
    -0.06
    POSITIVE LOGITS
    íĽĪ
    0.07
     gdy
    0.07
    metatable
    0.07
    peak
    0.07
    emsp
    0.07
    _PK
    0.07
    ãİ¡
    0.07
     Kimber
    0.07
    ÅĤÄħ
    0.07
    NullOr
    0.07
    Activations Density 0.012%

    No Known Activations