© 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. 58132
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "between."

    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
    mour
    -0.08
    zon
    -0.07
    جاÙĨ
    -0.07
    osate
    -0.07
    ovid
    -0.07
    çĴĥ
    -0.07
    roz
    -0.07
    .CO
    -0.07
    LES
    -0.07
    ncia
    -0.07
    POSITIVE LOGITS
     sexes
    0.08
    /am
    0.07
     ages
    0.07
    785
    0.07
     tack
    0.07
    zeit
    0.06
    ylül
    0.06
     thumb
    0.06
     Blank
    0.06
    760
    0.06
    Activations Density 0.012%

    No Known Activations