© 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. 56024
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate inclusion or listing

    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
    assen
    -0.08
    classCallCheck
    -0.07
    ãĥ«ãĥī
    -0.07
    baugh
    -0.07
     gridColumn
    -0.06
    ιÏİ
    -0.06
     hala
    -0.06
    زار
    -0.06
    others
    -0.06
    ieee
    -0.06
    POSITIVE LOGITS
     two
    0.08
     ones
    0.07
    ané
    0.07
    alla
    0.07
     entirely
    0.06
     an
    0.06
    Ïĥη
    0.06
    wise
    0.06
    lex
    0.06
     three
    0.06
    Activations Density 0.007%

    No Known Activations