© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61184
    Prev
    Next
    INDEX
    Explanations

    references to intellectualism or intellectual pursuits

    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
    elan
    -0.08
    ISCO
    -0.08
    asso
    -0.08
    aney
    -0.07
    alta
    -0.07
    eday
    -0.07
    -LAST
    -0.07
    asio
    -0.07
    day
    -0.07
    etler
    -0.07
    POSITIVE LOGITS
    lectual
    0.09
    ize
    0.09
    /math
    0.08
    ized
    0.08
    /sp
    0.07
    izes
    0.07
    /art
    0.06
    ROTO
    0.06
     giant
    0.06
    ually
    0.06
    Activations Density 0.006%

    No Known Activations