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. 43960
    Prev
    Next
    INDEX
    Explanations

    incident-related phrases or events with significant implications

    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
    entiful
    -0.08
    llx
    -0.08
    .LoggerFactory
    -0.08
    ewis
    -0.08
    ovit
    -0.08
    صÙĩ
    -0.08
    llib
    -0.08
    yleft
    -0.07
    EMPLARY
    -0.07
    ullan
    -0.07
    POSITIVE LOGITS
     kick
    0.14
     jump
    0.13
     catal
    0.13
     precip
    0.12
     gal
    0.11
     lead
    0.11
     led
    0.11
     spurred
    0.11
     prompted
    0.11
    ign
    0.10
    Activations Density 0.039%

    No Known Activations