© 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 EvalsExportsAPI 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. 76493
    Prev
    Next
    INDEX
    Explanations

    terms related to unique game mechanics or experiences

    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
    omor
    -0.08
    oose
    -0.06
    lez
    -0.06
    oldem
    -0.06
     Gast
    -0.06
     ÎĶεν
    -0.06
    carbon
    -0.06
    .fb
    -0.06
     undead
    -0.06
     Eis
    -0.06
    POSITIVE LOGITS
    afone
    0.07
     exploration
    0.07
     radio
    0.06
    avigate
    0.06
    iod
    0.06
    $MESS
    0.06
    ffen
    0.06
    ories
    0.06
    .fm
    0.06
     proced
    0.06
    Activations Density 0.001%

    No Known Activations