© 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. 74008
    Prev
    Next
    INDEX
    Explanations

    complex narrative themes 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
    'gc
    -0.07
    اÙĦÙĬ
    -0.06
    лекÑģ
    -0.06
    леж
    -0.06
    _chg
    -0.06
    aliases
    -0.06
    kers
    -0.06
    iba
    -0.05
    assage
    -0.05
    aza
    -0.05
    POSITIVE LOGITS
    íıī
    0.08
    vil
    0.07
     reviews
    0.07
     reviewers
    0.07
    ëĦ·
    0.07
     reviewer
    0.07
    elop
    0.07
     ìłľëª©
    0.07
     Review
    0.07
     Complaint
    0.07
    Activations Density 0.030%

    No Known Activations