© 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. 29302
    Prev
    Next
    INDEX
    Explanations

    references to image files and technical data

    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
    648
    -0.06
    ebek
    -0.06
     earn
    -0.06
    roit
    -0.06
    agal
    -0.06
    ie
    -0.06
    agan
    -0.05
     fat
    -0.05
     echo
    -0.05
    208
    -0.05
    POSITIVE LOGITS
    omanip
    0.07
    .bmp
    0.07
    _INCLUDED
    0.07
     Fires
    0.06
     Mandal
    0.06
    733
    0.06
    .png
    0.06
     веÑĢеÑģ
    0.06
    ær
    0.06
    Æ¡m
    0.06
    Activations Density 0.013%

    No Known Activations