© 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. 5250
    Prev
    Next
    INDEX
    Explanations

    numerical data and values

    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
    ssc
    -0.07
    ardu
    -0.07
    .poster
    -0.07
    erland
    -0.07
    bris
    -0.07
    edback
    -0.07
    tein
    -0.07
    Fld
    -0.07
    scal
    -0.07
    abo
    -0.06
    POSITIVE LOGITS
     âĵĺ
    0.06
     Graham
    0.06
    å¨
    0.06
     detail
    0.06
    æĺŃ
    0.06
    .authentication
    0.06
     details
    0.06
    iy
    0.05
    å°Ħ
    0.05
     Details
    0.05
    Activations Density 0.003%

    No Known Activations