© 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. 16882
    Prev
    Next
    INDEX
    Explanations

    references to financial metrics and organizations

    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
     chained
    -0.06
     dev
    -0.06
    nero
    -0.06
    ington
    -0.06
     chains
    -0.05
    errmsg
    -0.05
    _within
    -0.05
    abinet
    -0.05
    olla
    -0.05
    äll
    -0.05
    POSITIVE LOGITS
    ).__
    0.09
    á»ijn
    0.08
    Venue
    0.07
    Ring
    0.07
     Ring
    0.07
    ì¦Ŀ
    0.07
    deriv
    0.07
    StringEncoding
    0.07
    hosts
    0.07
    Neutral
    0.07
    Activations Density 0.009%

    No Known Activations