© 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. 75526
    Prev
    Next
    INDEX
    Explanations

    numerical data and their formatting, particularly dates and times

    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
    rio
    -0.09
     Pron
    -0.08
    inin
    -0.07
     завод
    -0.07
     condu
    -0.07
    è°
    -0.07
     колÑĮ
    -0.06
    /support
    -0.06
    ertia
    -0.06
     groove
    -0.06
    POSITIVE LOGITS
    anca
    0.06
     Ply
    0.06
    oton
    0.06
     Sheridan
    0.06
     Anc
    0.06
    .infinity
    0.06
    mary
    0.05
     thereof
    0.05
    icals
    0.05
    .ObjectId
    0.05
    Activations Density 0.004%

    No Known Activations