© 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. 15-LLAMASCOPE-RES-131K
    11. 87921
    Prev
    Next
    INDEX
    Explanations

    references to ticketing or travel arrangements

    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
    ullan
    -0.08
    ooter
    -0.06
    acock
    -0.06
     Reads
    -0.06
     Bu
    -0.06
     Sark
    -0.06
    æŁĦ
    -0.06
    olan
    -0.06
     Holl
    -0.06
     con
    -0.06
    POSITIVE LOGITS
    hey
    0.07
    bay
    0.07
    omp
    0.06
    mega
    0.06
    Ease
    0.06
    _rng
    0.06
    jax
    0.06
    oler
    0.06
    haul
    0.06
    ruta
    0.06
    Activations Density 0.001%

    No Known Activations