© 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. 107784
    Prev
    Next
    INDEX
    Explanations

    references to bananas in various contexts

    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
    hani
    -0.09
    lain
    -0.07
    NER
    -0.06
    iface
    -0.06
    364
    -0.06
    ed
    -0.06
    avanaugh
    -0.06
    _CAST
    -0.06
    usting
    -0.06
     Cherry
    -0.06
    POSITIVE LOGITS
    apolis
    0.09
    pit
    0.08
    itos
    0.08
    á»ı
    0.08
    opoly
    0.08
    oes
    0.08
    berger
    0.07
    embros
    0.07
    ¼
    0.07
    -shaped
    0.07
    Activations Density 0.002%

    No Known Activations