© 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. 9-LLAMASCOPE-RES-131K
    11. 95237
    Prev
    Next
    INDEX
    Explanations

    terms related to data and content analysis

    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
    ping
    -0.08
    057
    -0.07
    оÑĢон
    -0.07
    ccione
    -0.07
    afil
    -0.06
    ìŀ¥ìĿ´
    -0.06
    _TYPED
    -0.06
    osing
    -0.06
    ilters
    -0.06
    zsche
    -0.06
    POSITIVE LOGITS
    WE
    0.07
     ÙĦØŃ
    0.07
    issy
    0.06
    QualifiedName
    0.06
     Jacobs
    0.06
    abouts
    0.06
    alon
    0.06
    å´
    0.06
    flake
    0.06
     Rodgers
    0.06
    Activations Density 0.060%

    No Known Activations