© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40325
    Prev
    Next
    INDEX
    Explanations

    references to announcements regarding membership changes in conferences

    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
     PureComponent
    -0.08
    anio
    -0.07
    alat
    -0.07
    erset
    -0.07
    606
    -0.07
     lekker
    -0.07
    jong
    -0.07
    Called
    -0.07
    .dk
    -0.07
    -Sah
    -0.07
    POSITIVE LOGITS
     pun
    0.06
     Pun
    0.06
    uent
    0.06
    uen
    0.06
    ixe
    0.06
    .usage
    0.06
     Gems
    0.06
     intrig
    0.06
    _executor
    0.05
     Downtown
    0.05
    Activations Density 0.005%

    No Known Activations