© 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. 59089
    Prev
    Next
    INDEX
    Explanations

    references to dreams and dreaming phenomena

    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
    aurus
    -0.08
    _DESCRIPTOR
    -0.08
    /manage
    -0.08
    ábado
    -0.07
     neod
    -0.07
    éŁ¿
    -0.07
    ="__
    -0.07
    .scalablytyped
    -0.07
    esta
    -0.07
    imos
    -0.07
    POSITIVE LOGITS
    cape
    0.07
    er
    0.07
     involving
    0.07
     containing
    0.07
    ãĥªãĥ¼ãĤº
    0.06
    483
    0.06
    buz
    0.06
    zz
    0.06
    adr
    0.06
    Ïĥί
    0.06
    Activations Density 0.010%

    No Known Activations