© 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. 41237
    Prev
    Next
    INDEX
    Explanations

    names and titles of video games and their associated content

    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
    _TestCase
    -0.08
    RIX
    -0.07
    herits
    -0.07
    ÅĪ
    -0.06
    .Strings
    -0.06
    condition
    -0.06
    emann
    -0.06
    chwitz
    -0.06
    RIPT
    -0.06
    479
    -0.06
    POSITIVE LOGITS
     vs
    0.07
     next
    0.07
    amac
    0.07
    oris
    0.07
     POLL
    0.06
     alternate
    0.06
     Vs
    0.06
    esta
    0.06
    oste
    0.06
     versus
    0.06
    Activations Density 0.017%

    No Known Activations