© 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. 56556
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to various contexts

    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
    owler
    -0.07
    ulo
    -0.07
    ooth
    -0.06
     Hein
    -0.06
     Burnett
    -0.06
    INGTON
    -0.06
    /etc
    -0.06
     ÙĦÙĩ
    -0.06
     especially
    -0.06
    AMP
    -0.06
    POSITIVE LOGITS
    adero
    0.09
     whereas
    0.08
     compared
    0.08
    yre
    0.07
    outil
    0.07
     lô
    0.07
    izik
    0.06
     Whereas
    0.06
    FIELDS
    0.06
    огÑĥ
    0.06
    Activations Density 0.040%

    No Known Activations