© 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. 16536
    Prev
    Next
    INDEX
    Explanations

    references to software licenses and associated documentation

    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
     fg
    -0.07
    elin
    -0.06
    eller
    -0.06
    fg
    -0.06
    logen
    -0.06
    rnd
    -0.06
    ories
    -0.06
    !=
    -0.06
    heim
    -0.06
    indle
    -0.06
    POSITIVE LOGITS
    itch
    0.08
    AMPL
    0.07
    idla
    0.06
    polator
    0.06
    å¡
    0.06
    ůž
    0.06
    PRINTF
    0.06
    ÙĪÙĨا
    0.06
    alted
    0.06
    SSID
    0.06
    Activations Density 0.001%

    No Known Activations