© 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. 59048
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data, structures, and measurements

    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
     же
    -0.08
     ones
    -0.08
     of
    -0.08
    902
    -0.07
     schem
    -0.07
     |_|
    -0.06
    usan
    -0.06
    enes
    -0.06
     pros
    -0.06
    ead
    -0.06
    POSITIVE LOGITS
     itself
    0.08
    åıĬåħ¶
    0.08
    ollar
    0.07
    orgia
    0.07
    以åıĬ
    0.06
    æģ¯
    0.06
    StackNavigator
    0.06
    éĻ¢
    0.06
    errat
    0.06
    aterangepicker
    0.06
    Activations Density 0.136%

    No Known Activations