© 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. 103203
    Prev
    Next
    INDEX
    Explanations

    URLs and web links

    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
     Hutchinson
    -0.06
    âĢ¦↵
    -0.06
    naissance
    -0.06
    ace
    -0.06
    風
    -0.05
    line
    -0.05
     em
    -0.05
     (
    -0.05
    Âł
    -0.05
     por
    -0.05
    POSITIVE LOGITS
    ityEngine
    0.10
    FunctionFlags
    0.09
    istra
    0.09
    ebek
    0.09
    iaux
    0.09
    InParameter
    0.09
     carbohydr
    0.08
     è©ķ価
    0.08
    _Tis
    0.08
    CppClass
    0.08
    Activations Density 0.004%

    No Known Activations