© 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. 78499
    Prev
    Next
    INDEX
    Explanations

    nouns related to various types of establishments, events, and categories

    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
     ones
    -0.07
    /-
    -0.06
    udit
    -0.06
    ffer
    -0.06
     Henderson
    -0.06
    ought
    -0.06
    fds
    -0.06
     nhau
    -0.06
     turn
    -0.06
     Humph
    -0.06
    POSITIVE LOGITS
    quia
    0.08
    akedown
    0.08
    alic
    0.07
    Ñģол
    0.07
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.07
     samot
    0.07
     meiden
    0.07
    oret
    0.07
    ctl
    0.07
    TTY
    0.07
    Activations Density 0.040%

    No Known Activations