© 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. 15-LLAMASCOPE-RES-131K
    11. 61602
    Prev
    Next
    INDEX
    Explanations

    numerical data and comparisons

    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
    alink
    -0.07
    nell
    -0.07
    .newaxis
    -0.06
    upal
    -0.06
    üf
    -0.06
    quito
    -0.06
     pale
    -0.06
    inker
    -0.06
    浩
    -0.06
    ÑıÑģÑĮ
    -0.06
    POSITIVE LOGITS
     solely
    0.20
     pure
    0.17
     exclusively
    0.16
    pure
    0.15
     sole
    0.15
    Pure
    0.15
     Pure
    0.15
     Sole
    0.15
     purely
    0.15
    纯
    0.15
    Activations Density 0.175%

    No Known Activations