© 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. 41853
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components and interactions

    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
     âĨĴ↵↵
    -0.07
     Lens
    -0.07
     grave
    -0.07
    rawer
    -0.07
    datatable
    -0.07
    blr
    -0.07
    _nf
    -0.07
    Lens
    -0.07
    γγ
    -0.07
    oti
    -0.06
    POSITIVE LOGITS
    ìļ´ëį°
    0.07
     fields
    0.06
    oble
    0.06
    alim
    0.06
     initial
    0.06
    Į
    0.06
    apan
    0.06
    EXTERN
    0.06
    ~
    0.05
    XXX
    0.05
    Activations Density 0.012%

    No Known Activations