© 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. 15828
    Prev
    Next
    INDEX
    Explanations

    references to product availability and variations

    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
    htdocs
    -0.08
    UrlParser
    -0.07
    ationToken
    -0.07
     YYSTYPE
    -0.07
    /respond
    -0.07
    ctrine
    -0.07
    skyt
    -0.07
    ]=>
    -0.07
    ACL
    -0.07
    EDIA
    -0.07
    POSITIVE LOGITS
    ited
    0.06
     either
    0.06
    8
    0.06
     Minor
    0.06
     Mint
    0.06
    3
    0.06
     mole
    0.06
    4
    0.06
    _BOTH
    0.06
     única
    0.06
    Activations Density 0.006%

    No Known Activations