© 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. 60944
    Prev
    Next
    INDEX
    Explanations

    terms related to participation in activities or events

    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
    efeller
    -0.09
    OTH
    -0.08
    eres
    -0.08
    .dep
    -0.08
    isson
    -0.08
    Porno
    -0.08
    erie
    -0.07
    òa
    -0.07
    éIJĺ
    -0.07
    ITTER
    -0.07
    POSITIVE LOGITS
    ment
    0.08
    ance
    0.08
    /ex
    0.08
    ANCE
    0.07
    364
    0.06
     with
    0.06
    /part
    0.06
    led
    0.06
     ausp
    0.06
     fatal
    0.06
    Activations Density 0.014%

    No Known Activations