© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77979
    Prev
    Next
    INDEX
    Explanations

    references to guides, tips, and resources related to various topics

    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
    áÄį
    -0.07
     Prec
    -0.07
    ạ
    -0.06
    ucher
    -0.06
    ason
    -0.06
    Prec
    -0.06
    tas
    -0.06
     pepp
    -0.06
    anik
    -0.05
    yor
    -0.05
    POSITIVE LOGITS
    åIJ§
    0.08
    izio
    0.08
    /stdc
    0.08
    å½
    0.07
    arrant
    0.07
    cus
    0.07
     Hopefully
    0.07
     hopefully
    0.07
    olist
    0.07
    iglia
    0.07
    Activations Density 0.015%

    No Known Activations