© 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. 79557
    Prev
    Next
    INDEX
    Explanations

    elements related to gaming features and payouts

    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
    abcdefghijklmnop
    -0.07
    vincia
    -0.07
    ohana
    -0.07
    URLException
    -0.07
    istrat
    -0.07
    amilia
    -0.07
    Looper
    -0.06
    empor
    -0.06
     conc
    -0.06
    éric
    -0.06
    POSITIVE LOGITS
    alc
    0.07
    èĭ±
    0.07
     Wid
    0.06
     titular
    0.06
     Crate
    0.06
     Buckley
    0.06
     Bet
    0.06
    481
    0.06
     Bris
    0.06
    ÏĨÎŃ
    0.06
    Activations Density 0.008%

    No Known Activations