© 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. 82785
    Prev
    Next
    INDEX
    Explanations

    instances of inconsistency or unexpected occurrences

    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
    LEAN
    -0.07
    uuml
    -0.07
    oso
    -0.07
    utow
    -0.07
    icros
    -0.07
    лÑı
    -0.07
    uges
    -0.07
    ën
    -0.07
     Brit
    -0.07
    itial
    -0.07
    POSITIVE LOGITS
     Irish
    0.08
     Ireland
    0.07
     Ire
    0.07
    ewis
    0.07
    vc
    0.06
     Dublin
    0.06
    vest
    0.06
     Fitzgerald
    0.06
     Coc
    0.06
     Done
    0.06
    Activations Density 0.001%

    No Known Activations