© 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. 9-LLAMASCOPE-RES-131K
    11. 96721
    Prev
    Next
    INDEX
    Explanations

    names and terms related to various subjects, especially in literature and technology

    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
    Leaks
    -0.06
    ors
    -0.05
     dos
    -0.05
    andez
    -0.05
     Sierra
    -0.05
    agg
    -0.05
     Formal
    -0.05
     Brother
    -0.05
    OrDefault
    -0.05
    eln
    -0.05
    POSITIVE LOGITS
    MethodInfo
    0.08
    acific
    0.08
    ditor
    0.07
    imenti
    0.07
    IVA
    0.07
    ¸ı
    0.07
    mÃŃ
    0.06
    ëļ
    0.06
     Zhou
    0.06
    ideographic
    0.06
    Activations Density 0.192%

    No Known Activations