© 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. 5246
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and inquiries related to hypothetical scenarios

    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
    mouseout
    -0.07
    geme
    -0.07
    epad
    -0.06
    .bs
    -0.06
     Banana
    -0.06
    ior
    -0.06
     belle
    -0.06
    пÑĢимеÑĢ
    -0.06
     Canal
    -0.06
    _ATOM
    -0.06
    POSITIVE LOGITS
     Desert
    0.06
    APE
    0.06
    γη
    0.06
     desert
    0.06
    .DataContext
    0.06
     given
    0.06
    agged
    0.05
    Ïĩη
    0.05
    CEL
    0.05
     opportunity
    0.05
    Activations Density 0.007%

    No Known Activations