© 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. 17-LLAMASCOPE-RES-131K
    11. 116821
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations

    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
     halves
    -0.07
    ugged
    -0.06
    orent
    -0.06
     mos
    -0.06
    èŃ·
    -0.06
    velopment
    -0.06
    Mos
    -0.06
    stell
    -0.06
     dikke
    -0.05
    imag
    -0.05
    POSITIVE LOGITS
    ustos
    0.10
    ERGY
    0.09
    usta
    0.08
    _TICK
    0.07
    usto
    0.07
    coma
    0.07
    442
    0.07
    ERRU
    0.07
    macen
    0.07
    artin
    0.07
    Activations Density 0.047%

    No Known Activations