© 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. 82087
    Prev
    Next
    INDEX
    Explanations

    references to literary criticism and evaluations

    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
    ugins
    -0.06
    rels
    -0.06
    inis
    -0.06
     driver
    -0.06
    Exception
    -0.06
    onden
    -0.05
     workers
    -0.05
    796
    -0.05
     åĦ
    -0.05
     unusual
    -0.05
    POSITIVE LOGITS
    GLfloat
    0.07
    uisine
    0.07
    æŃ©
    0.07
    å¼¥
    0.07
    éģ¿
    0.07
    issen
    0.06
    aturas
    0.06
    ticker
    0.06
     (~(
    0.06
     comprom
    0.06
    Activations Density 0.020%

    No Known Activations