© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97391
    Prev
    Next
    INDEX
    Explanations

    references to levels in various contexts

    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
    ewing
    -0.08
    ffd
    -0.07
    inputEmail
    -0.07
    ozo
    -0.07
    erli
    -0.06
    ESA
    -0.06
    afen
    -0.06
    lio
    -0.06
    å®ļçļĦ
    -0.06
    ampie
    -0.06
    POSITIVE LOGITS
    ropolis
    0.07
    erc
    0.06
    scoped
    0.06
     Clement
    0.06
     Macro
    0.06
    363
    0.06
    tet
    0.06
     macro
    0.06
    439
    0.06
    uchar
    0.06
    Activations Density 0.011%

    No Known Activations