© 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. 128904
    Prev
    Next
    INDEX
    Explanations

    phrases associated with important information or recommendations

    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
    Occurred
    -0.08
    OPSIS
    -0.07
    ToDate
    -0.07
    IfExists
    -0.07
    OrNull
    -0.07
     @_
    -0.06
     aquÃŃ
    -0.06
     ØŃس
    -0.06
    imo
    -0.06
    .gstatic
    -0.06
    POSITIVE LOGITS
    leet
    0.06
     indul
    0.06
    ayer
    0.06
    غة
    0.06
    594
    0.06
    enberg
    0.05
    antha
    0.05
    sortable
    0.05
    inden
    0.05
     aka
    0.05
    Activations Density 0.021%

    No Known Activations