© 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. 79430
    Prev
    Next
    INDEX
    Explanations

    specific dates and events in history or sports

    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
     tinh
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    ereotype
    -0.07
    à¸Ńà¸ģ
    -0.07
    eax
    -0.07
    prites
    -0.06
    consts
    -0.06
    loadModel
    -0.06
    ple
    -0.06
    arel
    -0.06
    POSITIVE LOGITS
    ettel
    0.06
    ismet
    0.06
    878
    0.06
    ucz
    0.06
    ackbar
    0.06
    zie
    0.06
    ULSE
    0.06
    474
    0.06
    401
    0.05
    871
    0.05
    Activations Density 0.002%

    No Known Activations