© 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. 89392
    Prev
    Next
    INDEX
    Explanations

    specific details regarding financial or trading information

    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
    orney
    -0.09
    efe
    -0.07
    istique
    -0.07
    cola
    -0.06
    iph
    -0.06
     colleges
    -0.06
     meth
    -0.06
    á»Ļng
    -0.06
    ropol
    -0.06
    iche
    -0.06
    POSITIVE LOGITS
    æ²»
    0.07
    ugu
    0.07
    cha
    0.07
    CHAN
    0.07
    ëĬ
    0.07
    chosen
    0.07
     Voting
    0.07
     Zug
    0.06
    ÙĪراÙĨ
    0.06
    елен
    0.06
    Activations Density 0.002%

    No Known Activations