© 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 EvalsExportsinterp-engineNEWAPI 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. 54596
    Prev
    Next
    INDEX
    Explanations

    mentions of awards and recognitions in various contexts

    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
    dez
    -0.07
    dings
    -0.07
    oids
    -0.07
     Rating
    -0.06
     tolerated
    -0.06
    oki
    -0.06
    tures
    -0.06
    ooter
    -0.06
    /network
    -0.06
     Wahl
    -0.06
    POSITIVE LOGITS
     awarded
    0.10
     award
    0.08
    Award
    0.07
     bestowed
    0.07
     reserved
    0.07
     earned
    0.07
    award
    0.07
     Award
    0.07
    -winning
    0.07
    etro
    0.06
    Activations Density 0.034%

    No Known Activations