© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118412
    Prev
    Next
    INDEX
    Explanations

    references to software versioning and updates

    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
    iens
    -0.07
    ÃĹ↵↵
    -0.07
    оÑĢаз
    -0.07
    ÑģÑİ
    -0.06
    _INTERRUPT
    -0.06
    .qq
    -0.06
    preneur
    -0.06
    опÑĢи
    -0.06
     sẵn
    -0.06
    еÑģÑĮ
    -0.06
    POSITIVE LOGITS
    neau
    0.08
    arty
    0.06
     mach
    0.06
     pan
    0.06
    ReuseIdentifier
    0.06
    ernel
    0.06
     tr
    0.06
    زÙħ
    0.06
    arel
    0.06
    RootElement
    0.06
    Activations Density 0.000%

    No Known Activations