© 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. 5-LLAMASCOPE-RES-131K
    11. 126902
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and conditions

    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
    thic
    -0.07
    chio
    -0.07
    cket
    -0.07
    ught
    -0.07
    zew
    -0.07
    æĥħ
    -0.06
    pora
    -0.06
    onders
    -0.06
    llum
    -0.06
    hoff
    -0.06
    POSITIVE LOGITS
    apon
    0.06
    íĥĪ
    0.06
     bat
    0.06
    ÑĥÑĢÑģ
    0.06
     Schneider
    0.06
    olen
    0.06
    á»ı
    0.06
    107
    0.05
     negative
    0.05
    å°Ķ
    0.05
    Activations Density 0.098%

    No Known Activations