Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44206
    Prev
    Next
    INDEX
    Explanations

    phrases related to security and monitoring services

    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
    üzel
    -0.06
    iker
    -0.06
    yal
    -0.06
    openssl
    -0.06
    avax
    -0.06
    _EMIT
    -0.06
    andler
    -0.06
    alsa
    -0.06
    icator
    -0.05
    inker
    -0.05
    POSITIVE LOGITS
     unprecedented
    0.10
     visibility
    0.10
     gran
    0.10
     instant
    0.10
     immediate
    0.10
     anytime
    0.10
     instantaneous
    0.10
     near
    0.09
     unmatched
    0.09
     unparalleled
    0.09
    Activations Density 0.050%

    No Known Activations