© 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. 83838
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly dashes and hyphens

    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
     NÄĽm
    -0.07
    stal
    -0.07
    ór
    -0.06
     hatta
    -0.06
     nearby
    -0.06
    cle
    -0.06
    áo
    -0.06
    ism
    -0.06
    èo
    -0.06
     ours
    -0.06
    POSITIVE LOGITS
    rve
    0.07
    iscard
    0.07
    @student
    0.07
     Ful
    0.06
     sire
    0.06
     Despite
    0.06
    createFrom
    0.06
     While
    0.06
     Although
    0.06
     It
    0.06
    Activations Density 0.009%

    No Known Activations