© 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. 73038
    Prev
    Next
    INDEX
    Explanations

    architectural styles and related terms

    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
    lon
    -0.07
    lac
    -0.07
    fare
    -0.07
    ÌĨ
    -0.07
    ,set
    -0.07
    ãĥ¨
    -0.07
     Examiner
    -0.07
    ãģķãĤī
    -0.07
    hone
    -0.07
    loe
    -0.07
    POSITIVE LOGITS
    638
    0.07
    undi
    0.06
    urette
    0.06
    chedulers
    0.06
    chers
    0.06
    yonel
    0.06
    GetObject
    0.06
    oulder
    0.06
     [=[
    0.06
    gons
    0.06
    Activations Density 0.017%

    No Known Activations