© 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. 15-LLAMASCOPE-RES-131K
    11. 88008
    Prev
    Next
    INDEX
    Explanations

    requests for reader engagement or feedback

    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
     spatial
    -0.06
    ovah
    -0.06
    -temp
    -0.06
    ãĥ³ãĥī
    -0.06
     Spirit
    -0.06
     dist
    -0.05
     supply
    -0.05
    urai
    -0.05
    /cgi
    -0.05
    ared
    -0.05
    POSITIVE LOGITS
     weitere
    0.08
    Facade
    0.08
    ¤¤
    0.07
    Further
    0.07
    +","+
    0.07
    acco
    0.07
    :;↵
    0.07
    è¿Ľä¸ĢæŃ¥
    0.07
    ãĤ¹ãĤ³
    0.07
    .IContainer
    0.07
    Activations Density 0.008%

    No Known Activations