© 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. 86787
    Prev
    Next
    INDEX
    Explanations

    issues related to software or application performance

    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
    613
    -0.06
    à¹Ģà¸Ĺ
    -0.06
    242
    -0.06
    isia
    -0.06
    cas
    -0.06
     Baker
    -0.06
    mann
    -0.06
    θι
    -0.06
     Survivor
    -0.05
     divisible
    -0.05
    POSITIVE LOGITS
     nothing
    0.10
    nothing
    0.08
     NOTHING
    0.08
     nada
    0.08
     neither
    0.08
     Nothing
    0.08
     ниÑĩего
    0.07
    earer
    0.07
    بس
    0.07
    Nothing
    0.07
    Activations Density 0.009%

    No Known Activations