© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 100
    Prev
    Next
    INDEX
    Explanations

    terms related to items and entities significant in specific contexts, particularly in cultural or community references

    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
    astle
    -0.08
    uppen
    -0.07
    abox
    -0.07
    सर
    -0.07
    SystemService
    -0.07
    rient
    -0.07
    _flutter
    -0.07
    Plug
    -0.07
    _lot
    -0.07
    wl
    -0.07
    POSITIVE LOGITS
     yet
    0.07
     Cel
    0.06
    .inst
    0.06
     Compass
    0.06
    ær
    0.06
     instead
    0.05
    igne
    0.05
    ux
    0.05
    ène
    0.05
     be
    0.05
    Activations Density 0.057%

    No Known Activations