© 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. 59730
    Prev
    Next
    INDEX
    Explanations

    instances of versioning and metadata indicators in programming or documentation

    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
    orf
    -0.07
     Cru
    -0.06
    enha
    -0.06
    urgy
    -0.06
    esen
    -0.06
    olini
    -0.06
     Uploaded
    -0.06
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.06
    ropolis
    -0.06
    óÅĤ
    -0.06
    POSITIVE LOGITS
     copyright
    0.07
     COPYRIGHT
    0.07
    ilst
    0.07
    ontent
    0.07
     Copyright
    0.07
    copyright
    0.07
    regor
    0.06
    radu
    0.06
    ilde
    0.06
     ØŃÛĮ
    0.06
    Activations Density 0.002%

    No Known Activations