© 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. 128320
    Prev
    Next
    INDEX
    Explanations

    programming-related terms

    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
    usz
    -0.07
    auen
    -0.06
     Mare
    -0.06
    lica
    -0.06
     rewind
    -0.06
    gın
    -0.06
    itoris
    -0.06
    culus
    -0.06
    653
    -0.06
    arily
    -0.06
    POSITIVE LOGITS
    .annotations
    0.10
     Riders
    0.07
    urt
    0.07
     Chairman
    0.06
    /xhtml
    0.06
    s
    0.06
    setAttribute
    0.06
    _Equals
    0.06
    kr
    0.06
    -strokes
    0.06
    Activations Density 0.000%

    No Known Activations