© 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. 82043
    Prev
    Next
    INDEX
    Explanations

    words and phrases that imply directionality or action

    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
    chu
    -0.08
    aras
    -0.07
    íģ¼
    -0.07
    orman
    -0.07
    aps
    -0.07
    ic
    -0.07
    å¤Ł
    -0.07
    jos
    -0.07
    ¼åIJĪ
    -0.06
    еÑĢеÑĩ
    -0.06
    POSITIVE LOGITS
    amus
    0.08
    712
    0.07
     earlier
    0.07
    afort
    0.06
    oft
    0.06
     past
    0.06
    ngle
    0.06
    anners
    0.06
    itest
    0.06
    .Xaml
    0.06
    Activations Density 0.015%

    No Known Activations