© 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. 61591
    Prev
    Next
    INDEX
    Explanations

    specific nouns and phrases associated with impactful or significant phenomena

    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
    úÄįast
    -0.06
     lik
    -0.06
     Bir
    -0.06
    âĢ¦↵
    -0.06
     Mrs
    -0.05
    oldt
    -0.05
    ogh
    -0.05
     instead
    -0.05
    è±Ĭ
    -0.05
     I
    -0.05
    POSITIVE LOGITS
    .datab
    0.08
    ellen
    0.08
    æĸĹ
    0.08
    (EXPR
    0.08
    «ĺ
    0.08
    lemn
    0.07
     ******************************************************************************↵
    0.07
    GLenum
    0.07
     caut
    0.07
    ittest
    0.07
    Activations Density 0.194%

    No Known Activations