© 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. 84364
    Prev
    Next
    INDEX
    Explanations

    critiques of narrative structure and character development

    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
    åĪº
    -0.07
    ownt
    -0.06
    (compact
    -0.06
     StringComparison
    -0.06
    zyst
    -0.06
     möglich
    -0.06
    punk
    -0.06
     punct
    -0.06
    oku
    -0.06
     roli
    -0.06
    POSITIVE LOGITS
     too
    0.09
    too
    0.08
    -too
    0.08
     TOO
    0.08
     sometimes
    0.08
     太
    0.08
     artificial
    0.08
    AMI
    0.07
    mmc
    0.07
    Too
    0.07
    Activations Density 0.029%

    No Known Activations