© 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. 17-LLAMASCOPE-RES-131K
    11. 61539
    Prev
    Next
    INDEX
    Explanations

    file system paths and related directory structures

    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
     mixed
    -0.06
    averse
    -0.06
     lump
    -0.06
    aÅŁ
    -0.06
    acci
    -0.06
     bump
    -0.05
     attr
    -0.05
    bedo
    -0.05
    emann
    -0.05
     participant
    -0.05
    POSITIVE LOGITS
    bis
    0.07
    éĹĺ
    0.07
    olesale
    0.07
    \Desktop
    0.07
    Overrides
    0.07
    è
    0.07
    unts
    0.07
    istrator
    0.07
    \AppData
    0.06
    /src
    0.06
    Activations Density 0.004%

    No Known Activations