Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16539
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "have."

    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
    nech
    -0.08
    eprom
    -0.07
    quete
    -0.07
    usercontent
    -0.06
    RenderingContext
    -0.06
    EZ
    -0.06
    .neo
    -0.06
    ————
    -0.06
    -Sah
    -0.06
    ึà¹Ī
    -0.06
    POSITIVE LOGITS
     ourselves
    0.07
     we
    0.06
    DBC
    0.06
    бина
    0.06
     Across
    0.06
    iesen
    0.06
    ancia
    0.06
    обов
    0.06
     across
    0.06
     patch
    0.06
    Activations Density 0.000%

    No Known Activations