© 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. 15-LLAMASCOPE-RES-131K
    11. 61806
    Prev
    Next
    INDEX
    Explanations

    references to Fortune 500 companies and related metrics

    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
    ils
    -0.07
    esis
    -0.07
    gings
    -0.06
    nip
    -0.06
    venge
    -0.06
    urd
    -0.06
    nie
    -0.06
    ging
    -0.06
    velt
    -0.06
    eview
    -0.06
    POSITIVE LOGITS
    /Form
    0.07
    민êµŃ
    0.06
     обоÑĢ
    0.06
    <*
    0.06
    aux
    0.06
     ÙħØŃاÙģظ
    0.06
    awe
    0.06
    _PF
    0.06
     müz
    0.06
    ãģ©
    0.06
    Activations Density 0.001%

    No Known Activations