© 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. 14547
    Prev
    Next
    INDEX
    Explanations

    coordinates and numeric values related to graphical representations or data plots

    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
    printStats
    -0.09
    <LM
    -0.08
    $MESS
    -0.07
    ELLOW
    -0.07
    chod
    -0.07
    елик
    -0.07
    #aa
    -0.06
    ebx
    -0.06
    rray
    -0.06
    POSITE
    -0.06
    POSITIVE LOGITS
    anning
    0.06
     vrou
    0.06
    fy
    0.06
     Atkins
    0.06
     Mandal
    0.06
    ãģĭãģ«
    0.06
    ñana
    0.06
     Hanson
    0.05
     Goods
    0.05
    عب
    0.05
    Activations Density 0.023%

    No Known Activations