© 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. 108530
    Prev
    Next
    INDEX
    Explanations

    proper nouns and media-related terms

    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
    óz
    -0.07
    iegel
    -0.07
    è
    -0.06
    istributor
    -0.06
    erre
    -0.06
     Pierce
    -0.06
    ington
    -0.06
    eri
    -0.06
    pesan
    -0.06
     bi
    -0.06
    POSITIVE LOGITS
    -owned
    0.07
    社
    0.07
    zet
    0.07
    odus
    0.06
    æĹĹ
    0.06
    éĽĨåĽ¢
    0.06
    ìĤ¬ëĬĶ
    0.06
    ANDROID
    0.06
    odo
    0.06
     Group
    0.06
    Activations Density 0.010%

    No Known Activations