© 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 EvalsExportsAPI 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. 74950
    Prev
    Next
    INDEX
    Explanations

    non-English words or phrases

    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
    atz
    -0.07
    .RightToLeft
    -0.07
    ulet
    -0.07
    zone
    -0.06
    _THREADS
    -0.06
    üny
    -0.06
     pione
    -0.06
    ARAM
    -0.06
    wire
    -0.06
    .Android
    -0.06
    POSITIVE LOGITS
    crement
    0.06
    Got
    0.06
    mx
    0.06
     Eins
    0.06
     glyphicon
    0.06
    ÎIJ
    0.06
    egot
    0.06
    iler
    0.06
    _exempt
    0.06
    ë§ī
    0.06
    Activations Density 0.000%

    No Known Activations