© 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. 79402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ameda
    -0.09
    manship
    -0.08
    crest
    -0.08
    ery
    -0.08
    rys
    -0.07
    rna
    -0.07
    omite
    -0.07
    ãģ¡ãĤĥãĤĵ
    -0.07
    amba
    -0.07
    sworth
    -0.07
    POSITIVE LOGITS
    ingly
    0.08
     attempts
    0.07
     Attempts
    0.07
     attempt
    0.07
    yl
    0.07
    ä¸įåĪ°
    0.07
     situations
    0.06
    antly
    0.06
    lessly
    0.06
     Situation
    0.06
    Activations Density 0.008%

    No Known Activations