© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    references to the Pulitzer Prize

    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
    nip
    -0.09
    essim
    -0.07
    building
    -0.07
    aceut
    -0.07
    ailles
    -0.07
    iker
    -0.07
    edia
    -0.07
    nish
    -0.07
    gie
    -0.07
    onet
    -0.07
    POSITIVE LOGITS
    ian
    0.07
     Prize
    0.06
     prize
    0.06
    è³ŀ
    0.06
    ushima
    0.06
     Corporation
    0.06
     award
    0.06
    rious
    0.06
    ت
    0.06
    ten
    0.06
    Activations Density 0.002%

    No Known Activations