© 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. 79318
    Prev
    Next
    INDEX
    Explanations

    evaluation and assessment processes in a performance or selection context

    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
     seins
    -0.08
    ullen
    -0.07
    ä¹ĭä¸Ģ
    -0.07
    è·¡
    -0.07
    kla
    -0.07
    è¹
    -0.07
    evenodd
    -0.07
    ä¾ĭ
    -0.07
    ording
    -0.07
    iros
    -0.07
    POSITIVE LOGITS
     performance
    0.08
     performances
    0.06
    ences
    0.06
     whether
    0.06
     g
    0.06
     Mikhail
    0.06
     translator
    0.06
     Performance
    0.06
     potential
    0.06
    performance
    0.06
    Activations Density 0.014%

    No Known Activations