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. 43737
    Prev
    Next
    INDEX
    Explanations

    references to Greek drama and its components

    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
    RuleContext
    -0.08
    mojom
    -0.07
     Romero
    -0.07
    izm
    -0.07
    devil
    -0.07
     Americans
    -0.07
    OTTOM
    -0.07
    razier
    -0.07
    eneg
    -0.07
    .Undef
    -0.07
    POSITIVE LOGITS
     Lesbian
    0.13
     lyric
    0.12
     Lesb
    0.11
     Ion
    0.10
     Hom
    0.10
     Alexand
    0.10
     eleg
    0.09
     vase
    0.09
     Att
    0.09
     Ly
    0.09
    Activations Density 0.017%

    No Known Activations