© 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. 9-LLAMASCOPE-RES-131K
    11. 97060
    Prev
    Next
    INDEX
    Explanations

    instances of direct speech and quotes in the text

    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
    tip
    -0.06
    ÙĬدا
    -0.06
    ista
    -0.06
    ietet
    -0.06
    ultip
    -0.06
    .reverse
    -0.05
    reich
    -0.05
    ton
    -0.05
    gregate
    -0.05
     Chronicles
    -0.05
    POSITIVE LOGITS
    кÑĢаÑĹн
    0.07
    à¸ķล
    0.07
    siz
    0.07
    LEE
    0.07
     ballo
    0.07
    strand
    0.06
    awan
    0.06
    ابÙĬ
    0.06
    LOCKS
    0.06
    Compat
    0.06
    Activations Density 0.042%

    No Known Activations