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

    Neuronpedia

    Jacobian LensNEW
    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. 84316
    Prev
    Next
    INDEX
    Explanations

    references to different genres and scenes within music and literature

    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
    Äı
    -0.07
    _tac
    -0.07
    wort
    -0.07
    ÌĨ
    -0.07
    ptions
    -0.07
    Fx
    -0.06
    anche
    -0.06
    ocity
    -0.06
    P
    -0.06
     ChÃŃ
    -0.06
    POSITIVE LOGITS
    /Foundation
    0.07
    ToDevice
    0.07
    /{{
    0.06
    ihn
    0.06
    sie
    0.06
    ç©´
    0.06
    /android
    0.06
    ather
    0.06
    ãģªãĤī
    0.06
    ATHER
    0.06
    Activations Density 0.058%

    No Known Activations