© 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. 82898
    Prev
    Next
    INDEX
    Explanations

    references to purchasing options for a product

    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
    avana
    -0.06
    409
    -0.06
    leta
    -0.06
    ̣
    -0.06
    иÑģк
    -0.06
     Replies
    -0.06
    avity
    -0.06
    ầm
    -0.06
    .timeScale
    -0.06
     åľ
    -0.06
    POSITIVE LOGITS
    ults
    0.07
     Farrell
    0.06
    WER
    0.06
    breaking
    0.06
     Crowley
    0.06
    udi
    0.06
    Raised
    0.06
     mud
    0.06
    ±
    0.06
    าะ
    0.06
    Activations Density 0.000%

    No Known Activations