© 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. 105524
    Prev
    Next
    INDEX
    Explanations

    various forms of verbs related to action or condition

    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
    ãİ
    -0.08
    ÑıÑħ
    -0.08
    parallel
    -0.07
    afil
    -0.07
    ladu
    -0.07
    Äł
    -0.07
    ayer
    -0.07
    .setResult
    -0.07
    人çī©
    -0.07
    ết
    -0.07
    POSITIVE LOGITS
     whom
    0.09
     who
    0.09
    innen
    0.08
    who
    0.08
    stvo
    0.07
    ship
    0.07
     ارشد
    0.06
    614
    0.06
    ÑģÑĤво
    0.06
    们
    0.06
    Activations Density 0.041%

    No Known Activations