© 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. 71951
    Prev
    Next
    INDEX
    Explanations

    comparative language indicating degrees of performance or achievement

    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
    kaar
    -0.07
    cete
    -0.07
    agina
    -0.07
    yclopedia
    -0.07
    ette
    -0.07
    ÙıÙĪا
    -0.06
    Å¡li
    -0.06
    }elseif
    -0.06
    olley
    -0.06
    .sul
    -0.06
    POSITIVE LOGITS
     even
    0.16
    even
    0.13
     any
    0.11
     даже
    0.11
     EVEN
    0.10
     both
    0.09
     Even
    0.09
    çĶļèĩ³
    0.09
     than
    0.09
    Even
    0.08
    Activations Density 0.057%

    No Known Activations