© 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. 69973
    Prev
    Next
    INDEX
    Explanations

    expressions of community support and resilience

    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
    /stdc
    -0.08
    ÙĪراÙĨ
    -0.07
    _CONV
    -0.07
    ogie
    -0.06
    stamp
    -0.06
    abor
    -0.06
     Kraj
    -0.06
    apos
    -0.06
    yas
    -0.06
    geb
    -0.06
    POSITIVE LOGITS
     community
    0.14
    community
    0.12
    /community
    0.10
     Community
    0.10
    -community
    0.10
     communities
    0.10
    Community
    0.09
    社åĮº
    0.09
     spirit
    0.09
     comunidad
    0.08
    Activations Density 0.057%

    No Known Activations