© 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. 22-LLAMASCOPE-RES-131K
    11. 3958
    Prev
    Next
    INDEX
    Explanations

    references to film sensitivity ratings and standards

    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
    _graphics
    -0.06
     wz
    -0.06
    enco
    -0.06
    graphics
    -0.06
    ventory
    -0.06
    ength
    -0.06
    coc
    -0.06
    htt
    -0.06
    Connection
    -0.06
     circumference
    -0.06
    POSITIVE LOGITS
     INCIDENT
    0.08
     exposure
    0.08
     RAW
    0.08
     Exposure
    0.08
     exposures
    0.07
    Expose
    0.07
     Whites
    0.07
    æĽ
    0.07
    .DataBindings
    0.07
    RAW
    0.07
    Activations Density 0.006%

    No Known Activations