© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17227
    Prev
    Next
    INDEX
    Explanations

    conditional statements and responses

    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
    edd
    -0.06
    اÙĨÙĩ
    -0.06
    ib
    -0.06
    ordion
    -0.06
    ldb
    -0.06
    ç¾½
    -0.06
     Became
    -0.06
    fcn
    -0.06
    agi
    -0.06
    gov
    -0.06
    POSITIVE LOGITS
     failing
    0.15
     fails
    0.15
     failed
    0.14
     fail
    0.14
     If
    0.12
    failed
    0.12
     failure
    0.12
    If
    0.11
     Failed
    0.11
     Fail
    0.11
    Activations Density 0.056%

    No Known Activations