© 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. 120619
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional or preemptive actions

    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
    sla
    -0.07
    ç·Ĵ
    -0.07
    ibs
    -0.06
     Persistence
    -0.06
    à¸ģà¸ķ
    -0.06
     persistence
    -0.06
    ACKET
    -0.06
     Äijâu
    -0.06
    iba
    -0.06
    άλ
    -0.06
    POSITIVE LOGITS
     too
    0.09
     TOO
    0.07
     Too
    0.07
    otte
    0.07
    oute
    0.06
     vej
    0.06
    ottom
    0.06
     otherwise
    0.06
    lich
    0.06
    too
    0.06
    Activations Density 0.009%

    No Known Activations