© 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. 2170
    Prev
    Next
    INDEX
    Explanations

    terms associated with assessments and evaluations in various contexts

    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
    èĪĪ
    -0.06
    ondheim
    -0.06
    uxe
    -0.06
    lok
    -0.05
     наз
    -0.05
     confined
    -0.05
    lor
    -0.05
    ux
    -0.05
    ickle
    -0.05
    ima
    -0.05
    POSITIVE LOGITS
    already
    0.11
     already
    0.10
     Already
    0.10
    Already
    0.09
    popular
    0.09
     popular
    0.09
    å·²ç»ı
    0.09
     yıldır
    0.08
     попÑĥлÑıÑĢ
    0.08
    å·²
    0.08
    Activations Density 0.029%

    No Known Activations