© 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. 92624
    Prev
    Next
    INDEX
    Explanations

    instances of the word "start" and its variations indicating the commencement of actions or events

    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
    oya
    -0.08
    omp
    -0.08
    rouch
    -0.07
    Emitter
    -0.07
    achable
    -0.07
    lixir
    -0.07
     пÑĢодовж
    -0.07
    ACH
    -0.06
    öst
    -0.06
     ÙħتÙĪسط
    -0.06
    POSITIVE LOGITS
     to
    0.09
    636
    0.07
    347
    0.06
    uppen
    0.06
     making
    0.06
     Erotic
    0.06
    lero
    0.06
     paying
    0.06
     rast
    0.06
    643
    0.05
    Activations Density 0.024%

    No Known Activations