© 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. 125404
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used in quotations

    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
    骨
    -0.07
    owan
    -0.07
    ELS
    -0.06
    onen
    -0.06
    ût
    -0.06
    bud
    -0.06
    agra
    -0.06
    amarin
    -0.06
    ergus
    -0.06
    оÑĢе
    -0.06
    POSITIVE LOGITS
     etc
    0.08
    BaseContext
    0.07
    .connected
    0.07
     Peb
    0.06
     Hindered
    0.06
     Neville
    0.06
    åľ
    0.06
     Aires
    0.06
    ENA
    0.06
    etc
    0.06
    Activations Density 0.000%

    No Known Activations