© 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. 118677
    Prev
    Next
    INDEX
    Explanations

    critique related to character development and narrative depth

    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
    atty
    -0.07
    hea
    -0.07
    olon
    -0.06
    ellig
    -0.06
    ropol
    -0.06
    agger
    -0.06
    igin
    -0.06
    redits
    -0.06
    atte
    -0.06
    ).__
    -0.06
    POSITIVE LOGITS
     too
    0.08
     TOO
    0.07
     rather
    0.07
    Feels
    0.07
    LBL
    0.07
     seemed
    0.07
     felt
    0.07
    chez
    0.07
     zbyt
    0.06
     throughout
    0.06
    Activations Density 0.018%

    No Known Activations