© 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. 86319
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software settings and templates

    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
    asar
    -0.07
     frauen
    -0.07
    _SPI
    -0.07
    oro
    -0.07
    Å¡li
    -0.07
     kvin
    -0.06
    inke
    -0.06
    caf
    -0.06
    ular
    -0.06
     Hüs
    -0.06
    POSITIVE LOGITS
    ession
    0.07
    ponible
    0.06
    endi
    0.06
    agli
    0.06
    enance
    0.06
    ζη
    0.05
    ìĸ
    0.05
    ÏĩÏī
    0.05
    eut
    0.05
    ilder
    0.05
    Activations Density 0.000%

    No Known Activations