© 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. 76417
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotation marks in the text

    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
    anine
    -0.06
    ubb
    -0.06
    scp
    -0.06
    blink
    -0.06
     “
    -0.06
    obili
    -0.06
     Ack
    -0.06
     *,↵
    -0.06
     ”
    -0.06
    notated
    -0.06
    POSITIVE LOGITS
    лава
    0.07
    ych
    0.07
    hle
    0.07
     subtree
    0.07
    /'
    0.07
    WithContext
    0.06
    åħħ
    0.06
    ura
    0.06
    esel
    0.06
    adaki
    0.06
    Activations Density 0.036%

    No Known Activations