© 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. 9-LLAMASCOPE-RES-131K
    11. 97158
    Prev
    Next
    INDEX
    Explanations

    references to time and structure in narratives

    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
    abee
    -0.08
    ativ
    -0.08
    onto
    -0.07
    rieb
    -0.07
    esome
    -0.07
    ometr
    -0.07
    akis
    -0.07
    ụy
    -0.07
     primitive
    -0.07
    endregion
    -0.07
    POSITIVE LOGITS
    ãĥĥãĤ«ãĥ¼
    0.06
     киÑĢ
    0.06
    utsch
    0.06
    اÙĬÙĦ
    0.06
    alker
    0.06
    casting
    0.06
    Slow
    0.05
     Freel
    0.05
    chu
    0.05
     Slow
    0.05
    Activations Density 0.119%

    No Known Activations