© 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. 40002
    Prev
    Next
    INDEX
    Explanations

    variations of the word "all"

    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
    ew
    -0.08
     Folk
    -0.08
    ATAB
    -0.08
    ALCHEMY
    -0.08
    etwork
    -0.07
    ìŀĶ
    -0.07
    ame
    -0.07
    dest
    -0.07
    eb
    -0.07
    ยว
    -0.07
    POSITIVE LOGITS
     source
    0.09
     sources
    0.09
    /source
    0.08
    -source
    0.07
    /sources
    0.07
    (Source
    0.07
     getSource
    0.07
     Sources
    0.07
    (source
    0.07
    sources
    0.07
    Activations Density 0.002%

    No Known Activations