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. 43623
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation in equations

    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
    aeper
    -0.07
    -wsj
    -0.07
    ="../../../
    -0.07
    оÑĢаÑı
    -0.07
    $_
    -0.07
     addCriterion
    -0.06
    .learn
    -0.06
     (--
    -0.06
    iffin
    -0.06
    aland
    -0.05
    POSITIVE LOGITS
     Q
    0.11
     E
    0.10
     H
    0.10
     V
    0.10
     U
    0.10
     q
    0.10
     J
    0.09
     L
    0.09
     h
    0.09
     G
    0.09
    Activations Density 0.075%

    No Known Activations