© 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. 57375
    Prev
    Next
    INDEX
    Explanations

    terminologies and discussions related to computer systems and processes

    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
    ãģŁãģĦ
    -0.07
    ÌĤ
    -0.07
    lever
    -0.07
    ojis
    -0.07
     mo
    -0.07
    illez
    -0.06
     rud
    -0.06
    <<<
    -0.06
    agr
    -0.06
    OI
    -0.06
    POSITIVE LOGITS
     NONINFRINGEMENT
    0.07
    utt
    0.06
     DISCLAIMS
    0.06
    bÃŃ
    0.06
    roupe
    0.06
    plevel
    0.06
     favored
    0.06
    ληÏĤ
    0.06
    ìĽħ
    0.06
    ÅĻÃŃ
    0.06
    Activations Density 0.002%

    No Known Activations