© 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. 555
    Prev
    Next
    INDEX
    Explanations

    descriptors of artistic movements and scenes

    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
    ampa
    -0.07
     fra
    -0.07
    panion
    -0.06
    ispecies
    -0.06
    phins
    -0.06
    úa
    -0.06
    ÏĦÎŃ
    -0.06
    ò
    -0.06
    arro
    -0.06
     tod
    -0.06
    POSITIVE LOGITS
     local
    0.10
     LOCAL
    0.09
    (local
    0.09
    -local
    0.08
    local
    0.08
     locally
    0.08
    _LOCAL
    0.08
     Local
    0.08
    LOCAL
    0.08
     locals
    0.07
    Activations Density 0.017%

    No Known Activations