© 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. 15-LLAMASCOPE-RES-131K
    11. 87883
    Prev
    Next
    INDEX
    Explanations

    phrases indicating items that are not included in a purchase or package

    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
    vio
    -0.08
    она
    -0.07
     hend
    -0.07
    ä¸ĭåİ»
    -0.07
    ombo
    -0.06
     inters
    -0.06
    klass
    -0.06
    ождение
    -0.06
    ilit
    -0.06
    _IDX
    -0.06
    POSITIVE LOGITS
    raham
    0.06
     Doyle
    0.06
    elocity
    0.06
     convenience
    0.06
    Triple
    0.06
    esome
    0.06
     pa
    0.06
    iyan
    0.06
     licenses
    0.06
     mine
    0.06
    Activations Density 0.006%

    No Known Activations