© 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. 27640
    Prev
    Next
    INDEX
    Explanations

    references to online documents and web resources

    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
    Ñģли
    -0.07
    edis
    -0.07
    camel
    -0.06
    dess
    -0.06
    edy
    -0.06
    ofday
    -0.06
    etch
    -0.06
     stakes
    -0.06
    antee
    -0.06
    annon
    -0.06
    POSITIVE LOGITS
    ÅĻad
    0.08
    ãģ¾ãģĽãĤĵ
    0.07
    èĮĤ
    0.06
    znik
    0.06
    onen
    0.06
    iene
    0.06
    ISING
    0.06
    ált
    0.06
    ëĮ
    0.06
    ICO
    0.06
    Activations Density 0.009%

    No Known Activations