© 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 EvalsExportsinterp-engineNEWAPI 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. 87884
    Prev
    Next
    INDEX
    Explanations

    phrases indicating academic achievements and contributions

    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
     hind
    -0.07
    zen
    -0.06
    hind
    -0.06
    опÑĢи
    -0.06
    etur
    -0.06
    oi
    -0.06
    able
    -0.06
    izon
    -0.06
    ush
    -0.05
    agra
    -0.05
    POSITIVE LOGITS
     célib
    0.08
    Charsets
    0.07
    iders
    0.07
    PointerException
    0.07
    воÑİ
    0.07
    OCUS
    0.07
     suce
    0.07
    ascus
    0.07
    æĮĤ
    0.07
    .VisualBasic
    0.07
    Activations Density 0.008%

    No Known Activations