© 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. 81407
    Prev
    Next
    INDEX
    Explanations

    references to dimensions and measurements, particularly widths

    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
    ber
    -0.07
    loff
    -0.07
    roll
    -0.07
    arend
    -0.07
    eh
    -0.07
    eks
    -0.07
    ood
    -0.07
    머ëĭĪ
    -0.06
    hti
    -0.06
     Jae
    -0.06
    POSITIVE LOGITS
    ened
    0.09
    pread
    0.09
    =device
    0.08
    MeasureSpec
    0.08
    robe
    0.08
    ening
    0.07
    wise
    0.07
    ãĥ§
    0.07
    ning
    0.07
    gang
    0.07
    Activations Density 0.021%

    No Known Activations