© 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. 83577
    Prev
    Next
    INDEX
    Explanations

    references to potential risks and uncertainties in forward-looking statements

    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
     Wr
    -0.07
    _FM
    -0.06
    ек
    -0.06
    485
    -0.05
    wright
    -0.05
     Madonna
    -0.05
    ç»ı
    -0.05
    974
    -0.05
     Yan
    -0.05
    ð
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    -factor
    0.08
    оÑĢоз
    0.07
    mobx
    0.07
     Crescent
    0.07
    .scalablytyped
    0.07
    ủi
    0.07
     Dün
    0.07
    abei
    0.07
     factor
    0.07
    Activations Density 0.001%

    No Known Activations