© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82973
    Prev
    Next
    INDEX
    Explanations

    references to significant dates and events related to health or legal matters

    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
    731
    -0.08
    559
    -0.07
    æ®Ĭ
    -0.07
    .ibm
    -0.07
    308
    -0.07
    dera
    -0.07
    uity
    -0.06
    mall
    -0.06
    avec
    -0.06
    nar
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.10
    ÑĤо
    0.07
    UZ
    0.07
    abus
    0.06
    iales
    0.06
    cul
    0.06
    alen
    0.06
    _cp
    0.06
    SCALE
    0.06
    acin
    0.06
    Activations Density 0.078%

    No Known Activations