© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87932
    Prev
    Next
    INDEX
    Explanations

    statements related to unexpected findings and differences in data results

    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
    lys
    -0.07
    recent
    -0.07
    .builders
    -0.07
    /respond
    -0.07
     Recent
    -0.07
    bedo
    -0.07
     rodiny
    -0.06
    ãģ£ãģ¦ãģĦ
    -0.06
     purch
    -0.06
     putas
    -0.06
    POSITIVE LOGITS
     results
    0.14
     findings
    0.11
     finding
    0.10
     unexpected
    0.10
     surprise
    0.10
     result
    0.10
    results
    0.09
    ç»ĵæŀľ
    0.09
     unexpectedly
    0.09
     found
    0.09
    Activations Density 0.047%

    No Known Activations