© 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. 78536
    Prev
    Next
    INDEX
    Explanations

    formatted text and LaTeX commands in a document

    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
    cke
    -0.09
    uche
    -0.07
    ehler
    -0.07
    Ñıк
    -0.07
    ucks
    -0.07
    orum
    -0.07
    azio
    -0.07
    edi
    -0.07
    rending
    -0.07
    unge
    -0.06
    POSITIVE LOGITS
    WWW
    0.06
     tun
    0.06
    ftware
    0.06
     tune
    0.06
     boy
    0.06
    ãģ¾ãģĽ
    0.05
     Cra
    0.05
     Vill
    0.05
     representation
    0.05
    733
    0.05
    Activations Density 0.015%

    No Known Activations