© 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. 91994
    Prev
    Next
    INDEX
    Explanations

    timestamps in a time format

    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
    UBLE
    -0.06
    innie
    -0.06
    Äħż
    -0.06
     tod
    -0.06
    IDDEN
    -0.06
    ritten
    -0.06
     Lose
    -0.05
    idden
    -0.05
    -events
    -0.05
    jourd
    -0.05
    POSITIVE LOGITS
    _PM
    0.07
    Îļα
    0.07
    éł
    0.06
    اÙĬÙĨ
    0.06
    otron
    0.06
    .Generated
    0.06
    ÑĢон
    0.06
    ượng
    0.06
    ìķħ
    0.06
    ÑĤÑİ
    0.06
    Activations Density 0.001%

    No Known Activations