© 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. 17-LLAMASCOPE-RES-131K
    11. 107838
    Prev
    Next
    INDEX
    Explanations

    technical information related to programming and coding practices

    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
     dedicated
    -0.07
     manufacturers
    -0.07
    amarin
    -0.06
    setDefault
    -0.06
    abh
    -0.06
    ools
    -0.06
     conduct
    -0.06
    ngrx
    -0.06
    Jvm
    -0.06
    ãĥ¼ãĥ«
    -0.05
    POSITIVE LOGITS
    代çłģ
    0.10
     code
    0.09
     Code
    0.08
    _code
    0.08
     código
    0.08
     ì½Ķëĵľ
    0.08
    Code
    0.08
    ãĤ³ãĥ¼ãĥī
    0.08
    _CODE
    0.07
    .code
    0.07
    Activations Density 0.021%

    No Known Activations