© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71730
    Prev
    Next
    INDEX
    Explanations

    articles that introduce and describe various characteristics or qualities

    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
     older
    -0.06
     Hat
    -0.05
     overlook
    -0.05
     other
    -0.05
     _
    -0.05
     Tol
    -0.05
     hat
    -0.05
    ependency
    -0.05
     ça
    -0.05
    ácil
    -0.05
    POSITIVE LOGITS
    TestCategory
    0.08
    osi
    0.08
    ionic
    0.08
    ì²
    0.07
    éį
    0.07
    noch
    0.07
    assen
    0.07
    ovna
    0.07
    icon
    0.07
    ijľ
    0.07
    Activations Density 0.028%

    No Known Activations