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

    Neuronpedia

    Jacobian LensNEW
    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. 78548
    Prev
    Next
    INDEX
    Explanations

    references to outdoor advertising and associated statistics

    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
    ocale
    -0.06
     Jennings
    -0.06
    enko
    -0.06
     Eisen
    -0.06
    agara
    -0.06
     impro
    -0.06
     exc
    -0.06
     boiler
    -0.06
    ationToken
    -0.06
    licht
    -0.06
    POSITIVE LOGITS
    vertising
    0.08
    akit
    0.07
     street
    0.07
    ivals
    0.07
     outdoor
    0.07
    eldorf
    0.07
    Street
    0.07
    _terminal
    0.07
    _street
    0.07
    ãĤ¾
    0.07
    Activations Density 0.011%

    No Known Activations