© 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. 72630
    Prev
    Next
    INDEX
    Explanations

    conditional statements or clauses

    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
    atto
    -0.07
    eref
    -0.07
    uddy
    -0.06
    bih
    -0.06
     gezocht
    -0.06
    andom
    -0.06
    lol
    -0.06
    tees
    -0.06
    adder
    -0.06
    andon
    -0.06
    POSITIVE LOGITS
     found
    0.10
     finds
    0.09
    found
    0.08
    -found
    0.08
    maal
    0.08
     Found
    0.07
    Find
    0.07
    (found
    0.07
     then
    0.07
     finding
    0.07
    Activations Density 0.023%

    No Known Activations