© 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. 90328
    Prev
    Next
    INDEX
    Explanations

    references to various time periods, particularly years and weeks

    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
    iani
    -0.09
    eward
    -0.07
    235
    -0.07
    ported
    -0.06
    Ñİк
    -0.06
    ÑĥÑģÑĤа
    -0.06
    iaux
    -0.06
    å±ķ
    -0.06
    ekten
    -0.06
    usch
    -0.05
    POSITIVE LOGITS
    ìī¬
    0.08
    Å¡en
    0.07
     Äijá»ĵng
    0.07
    uan
    0.07
     onDataChange
    0.07
     Соб
    0.07
    DITION
    0.06
    antan
    0.06
    \e
    0.06
     componentDidUpdate
    0.06
    Activations Density 0.021%

    No Known Activations