© 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. 62005
    Prev
    Next
    INDEX
    Explanations

    references to specific types of books and publications

    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
    ç·
    -0.07
    ÄĻ
    -0.07
    IVEN
    -0.06
    xF
    -0.06
    ritel
    -0.06
     Sou
    -0.06
    pers
    -0.06
    XP
    -0.06
     aspects
    -0.06
     GRAT
    -0.06
    POSITIVE LOGITS
    aukee
    0.08
    /New
    0.07
    /Edit
    0.07
    emble
    0.07
    swire
    0.06
    (old
    0.06
    æŧ
    0.06
     Zealand
    0.06
     acquainted
    0.06
    sworth
    0.06
    Activations Density 0.059%

    No Known Activations