© 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. 56973
    Prev
    Next
    INDEX
    Explanations

    references to "Small" in various contexts, particularly related to organizations or locations

    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
    ìľ¨
    -0.07
    AGES
    -0.07
    Ñĩив
    -0.07
    CDATA
    -0.07
    ected
    -0.06
    anel
    -0.06
    ungi
    -0.06
     Nay
    -0.06
    kop
    -0.06
    ety
    -0.06
    POSITIVE LOGITS
     Small
    0.07
    _kb
    0.06
    592
    0.06
     Fol
    0.06
    OLDER
    0.06
    anzeigen
    0.06
    Small
    0.06
     fing
    0.06
    iento
    0.06
     Format
    0.06
    Activations Density 0.019%

    No Known Activations