© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 94524
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "bud" and its variations, indicating a focus on cannabis or related topics

    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
    orp
    -0.07
    IAL
    -0.07
    ial
    -0.07
    yen
    -0.06
    een
    -0.06
     fluids
    -0.06
    furt
    -0.06
    abil
    -0.06
    ned
    -0.06
    stå
    -0.06
    POSITIVE LOGITS
    apest
    0.11
    sock
    0.07
    ger
    0.07
    ri
    0.07
    eto
    0.07
    ette
    0.06
    imen
    0.06
    enko
    0.06
    åĢ
    0.06
    alink
    0.06
    Activations Density 0.006%

    No Known Activations