© 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. 59939
    Prev
    Next
    INDEX
    Explanations

    references to experiences and locations related to a community or program

    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
    زÙĩ
    -0.06
    .scalablytyped
    -0.06
     comm
    -0.06
    bero
    -0.06
     insp
    -0.06
    еко
    -0.06
     HQ
    -0.06
    _CYCLE
    -0.06
    gem
    -0.06
    åĭ
    -0.06
    POSITIVE LOGITS
     at
    0.07
    onta
    0.06
    /generated
    0.06
    ylon
    0.06
    iage
    0.06
    usk
    0.06
    ipers
    0.06
    weis
    0.06
     Mour
    0.06
    ilight
    0.06
    Activations Density 0.080%

    No Known Activations