© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 88316
    Prev
    Next
    INDEX
    Explanations

    indicative phrases and elements of character development 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
    Reviewed
    -0.07
    ero
    -0.07
    olumn
    -0.06
    efd
    -0.06
    fic
    -0.06
    jvu
    -0.06
    tas
    -0.06
    ÏĬ
    -0.06
    69
    -0.06
    793
    -0.06
    POSITIVE LOGITS
     tale
    0.08
    ichert
    0.08
    çīĩ
    0.07
     nov
    0.07
    .gg
    0.07
    ffen
    0.06
    owi
    0.06
    ometr
    0.06
     Examination
    0.06
    rax
    0.06
    Activations Density 0.009%

    No Known Activations