© 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. 15-LLAMASCOPE-RES-131K
    6. 89816
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on."

    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
    allo
    -0.07
    ugged
    -0.07
    uzz
    -0.06
    æķ
    -0.06
     Code
    -0.06
    तर
    -0.05
    á»ĵng
    -0.05
    /wiki
    -0.05
    ullo
    -0.05
    cimal
    -0.05
    POSITIVE LOGITS
     sak
    0.08
    Ñĩен
    0.07
    oho
    0.07
    iguiente
    0.07
    صر
    0.06
    åĦĢ
    0.06
    vid
    0.06
    ocal
    0.06
    :|
    0.06
    aign
    0.06
    Activations Density 0.008%

    No Known Activations