© 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. 85905
    Prev
    Next
    INDEX
    Explanations

    phrases specifically referencing "Once Upon a Time."

    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
    ợ
    -0.07
    ãĤŃãĥ¥
    -0.07
    udit
    -0.06
     pseud
    -0.06
    points
    -0.06
    akin
    -0.06
    avec
    -0.06
    _FLUSH
    -0.06
    imiter
    -0.06
     move
    -0.06
    POSITIVE LOGITS
    ettle
    0.07
     REGARD
    0.07
    adu
    0.07
    otts
    0.07
    ufe
    0.06
    tras
    0.06
    324
    0.06
     ÄijÃŃch
    0.06
    brig
    0.06
    rades
    0.06
    Activations Density 0.001%

    No Known Activations