© 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. 93821
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something significantly impactful or noteworthy happening globally

    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
    utow
    -0.09
    atum
    -0.08
    itura
    -0.07
     Universe
    -0.07
    ylie
    -0.06
     itemprop
    -0.06
    itud
    -0.06
    course
    -0.06
     gratuita
    -0.06
    ionales
    -0.06
    POSITIVE LOGITS
     storm
    0.08
     hook
    0.07
     surprise
    0.06
     virtue
    0.06
     Storm
    0.06
     means
    0.06
     Hook
    0.06
    Storm
    0.06
    hel
    0.06
    _locs
    0.06
    Activations Density 0.002%

    No Known Activations