© 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. 71942
    Prev
    Next
    INDEX
    Explanations

    instances of promotional or entertainment-related content

    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
    "C
    -0.06
    usercontent
    -0.06
    uchs
    -0.06
     Cumhur
    -0.06
    uchen
    -0.06
    /container
    -0.06
     Copp
    -0.05
    CEL
    -0.05
    thew
    -0.05
     associative
    -0.05
    POSITIVE LOGITS
    559
    0.07
    oger
    0.06
    ccount
    0.06
     Substance
    0.06
    UCT
    0.06
    acket
    0.06
    949
    0.06
    abbo
    0.06
    affer
    0.06
    cket
    0.06
    Activations Density 0.016%

    No Known Activations