© 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. 73118
    Prev
    Next
    INDEX
    Explanations

    terms related to film and the arts

    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
    inki
    -0.07
    åı·
    -0.07
    stown
    -0.07
    ardu
    -0.07
    engkap
    -0.07
    ÃŃrk
    -0.06
    reso
    -0.06
     pinch
    -0.06
    ipay
    -0.06
    è¡Ĩ
    -0.06
    POSITIVE LOGITS
     Society
    0.08
     Heaven
    0.06
     program
    0.06
     Festival
    0.06
     society
    0.06
    :async
    0.06
    alon
    0.06
    anon
    0.06
    pery
    0.06
    оÑĢони
    0.06
    Activations Density 0.033%

    No Known Activations