© 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. 54649
    Prev
    Next
    INDEX
    Explanations

    titles and names associated with television shows

    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
    ICA
    -0.07
     EVENT
    -0.07
     Event
    -0.07
    asha
    -0.06
    ippi
    -0.06
     Merchant
    -0.06
    las
    -0.06
     event
    -0.06
    imbus
    -0.06
    ãĥ¶æľĪ
    -0.06
    POSITIVE LOGITS
     hosts
    0.08
     host
    0.07
    ento
    0.07
    SPATH
    0.07
     hosted
    0.07
    گراÙĨ
    0.06
     EXTRA
    0.06
    -host
    0.06
     Host
    0.06
     transcripts
    0.06
    Activations Density 0.024%

    No Known Activations