© 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. 76093
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attempts or efforts to perform an action

    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
    lett
    -0.08
    /mit
    -0.08
    .scalablytyped
    -0.08
    enstein
    -0.07
    enders
    -0.07
     mil
    -0.07
    icable
    -0.07
    ÑĢап
    -0.07
    sein
    -0.07
    lej
    -0.07
    POSITIVE LOGITS
    ansom
    0.06
    ë¡ł
    0.06
     Barcode
    0.06
    ¤í
    0.06
     perfectly
    0.06
    istrovstvÃŃ
    0.06
    413
    0.06
    aille
    0.06
    lopen
    0.06
    bedo
    0.06
    Activations Density 0.011%

    No Known Activations