© 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. 15-LLAMASCOPE-RES-131K
    11. 27642
    Prev
    Next
    INDEX
    Explanations

    code snippets or functions related to setting or returning values

    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
     eer
    -0.06
    pt
    -0.06
    986
    -0.06
     Roy
    -0.06
    ase
    -0.06
    sole
    -0.06
    bot
    -0.05
     Goldman
    -0.05
    igr
    -0.05
    914
    -0.05
    POSITIVE LOGITS
    opher
    0.09
     Shemale
    0.08
    appen
    0.08
     Qed
    0.08
    enties
    0.08
    ystack
    0.07
    FML
    0.07
    bage
    0.07
     cocos
    0.07
    suite
    0.07
    Activations Density 0.001%

    No Known Activations