© 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. 125768
    Prev
    Next
    INDEX
    Explanations

    time 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
    stor
    -0.06
    ÑģÑĥ
    -0.06
    ds
    -0.06
    oin
    -0.06
     Cr
    -0.05
    29
    -0.05
     versus
    -0.05
    orum
    -0.05
     Dir
    -0.05
    imer
    -0.05
    POSITIVE LOGITS
    ìĬĪ
    0.08
    оÑĤо
    0.07
    _bag
    0.07
    StackNavigator
    0.07
    ibs
    0.07
    akk
    0.07
    agos
    0.07
    èģĶç½ij
    0.07
    NCY
    0.07
    HandlerContext
    0.07
    Activations Density 0.001%

    No Known Activations