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. 11428
    Prev
    Next
    INDEX
    Explanations

    phrases and contexts related to significant changes or developments

    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
    rong
    -0.07
    ADDE
    -0.07
    ekil
    -0.06
    VERTISE
    -0.06
    lew
    -0.06
    ugins
    -0.06
    opis
    -0.06
    adir
    -0.06
    radan
    -0.06
    isphere
    -0.06
    POSITIVE LOGITS
     remains
    0.11
     likely
    0.10
     depends
    0.10
     remain
    0.10
    'll
    0.10
     depend
    0.09
     uncertainty
    0.09
    'd
    0.09
     presumably
    0.09
     uncertain
    0.09
    Activations Density 0.041%

    No Known Activations