© 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. 54509
    Prev
    Next
    INDEX
    Explanations

    references to specific dates, particularly months and years

    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
    CHK
    -0.06
    ông
    -0.06
    eras
    -0.06
    á»Ļn
    -0.06
    Ïģο
    -0.06
    privation
    -0.06
    ẻ
    -0.06
    илÑĮ
    -0.05
    ond
    -0.05
    esty
    -0.05
    POSITIVE LOGITS
    201
    0.14
    200
    0.12
    199
    0.10
    202
    0.10
    198
    0.09
    yonel
    0.07
    717
    0.07
    197
    0.07
    ilyn
    0.07
    jing
    0.07
    Activations Density 0.025%

    No Known Activations