© 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. 9-LLAMASCOPE-RES-131K
    6. 95205
    Prev
    Next
    INDEX
    Explanations

    occurrences of verbs and gerunds in various contexts

    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
    alc
    -0.07
    WHITE
    -0.06
    Ñģим
    -0.06
     bir
    -0.06
     Cres
    -0.06
     gaz
    -0.06
     intens
    -0.06
    IDS
    -0.06
     Shields
    -0.06
     Welsh
    -0.06
    POSITIVE LOGITS
    iband
    0.07
    .metro
    0.07
    metic
    0.07
    rå
    0.06
    metis
    0.06
    ombine
    0.06
    izons
    0.06
    inet
    0.06
    ülü
    0.06
    LARI
    0.06
    Activations Density 0.011%

    No Known Activations