© 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. 5-LLAMASCOPE-RES-131K
    11. 125793
    Prev
    Next
    INDEX
    Explanations

    references to heavy machinery and equipment

    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
    ivamente
    -0.06
    /up
    -0.06
     Excellence
    -0.06
    íħĶ
    -0.06
    ucas
    -0.06
     conclusion
    -0.06
    isse
    -0.05
    ãĤ£
    -0.05
    uses
    -0.05
    orig
    -0.05
    POSITIVE LOGITS
    weights
    0.08
    Æ°Æ¡ng
    0.08
    dre
    0.08
     Sunder
    0.07
    ink
    0.07
     Kız
    0.07
    -duty
    0.07
    uitka
    0.07
    ICODE
    0.07
    arts
    0.07
    Activations Density 0.008%

    No Known Activations