© 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. 88545
    Prev
    Next
    INDEX
    Explanations

    code-related terms and operations

    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
    acz
    -0.07
     اÙĦØŃر
    -0.07
    _mgmt
    -0.07
    èĵ
    -0.07
    ãĥ¼ãĥł
    -0.06
    боÑĢа
    -0.06
    avel
    -0.06
     Recycling
    -0.06
    ulum
    -0.06
    andon
    -0.06
    POSITIVE LOGITS
     diffs
    0.08
    diff
    0.08
     diff
    0.08
    ëĿ¼ìĿ¸
    0.07
    .diff
    0.07
     comparison
    0.07
     comparing
    0.07
     Diff
    0.07
     between
    0.07
     differences
    0.07
    Activations Density 0.005%

    No Known Activations