© 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. 27334
    Prev
    Next
    INDEX
    Explanations

    references to programming libraries and frameworks

    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
    ayette
    -0.06
    isher
    -0.06
    esis
    -0.06
     screen
    -0.06
     punch
    -0.06
    reen
    -0.06
     MatSnackBar
    -0.06
     seen
    -0.06
    itten
    -0.05
    innitus
    -0.05
    POSITIVE LOGITS
    slashes
    0.07
    ieri
    0.07
    asca
    0.07
    tae
    0.07
    wow
    0.07
    msp
    0.07
    .toFloat
    0.07
    utt
    0.07
     defaultManager
    0.07
    linger
    0.07
    Activations Density 0.000%

    No Known Activations