© 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. 29214
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs that indicate quantity or frequency

    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
    ProgressHUD
    -0.07
    ugen
    -0.07
    .scalablytyped
    -0.07
    ëł´
    -0.06
     Richt
    -0.06
    çº
    -0.06
     Crescent
    -0.06
    ammers
    -0.06
    ephir
    -0.06
    termin
    -0.06
    POSITIVE LOGITS
    vido
    0.07
     resulting
    0.06
    ttp
    0.06
    elsen
    0.06
    alem
    0.06
    ghost
    0.06
    eday
    0.06
    reff
    0.06
    _except
    0.06
    otp
    0.06
    Activations Density 0.041%

    No Known Activations