© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87724
    Prev
    Next
    INDEX
    Explanations

    titles or names related to arts, culture, and literature

    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
    ÙĪزÛĮ
    -0.07
     addCriterion
    -0.07
     isolate
    -0.07
    ,eg
    -0.07
    alth
    -0.06
    ãĥ³ãĥĩãĤ£
    -0.06
     lô
    -0.06
    OUCH
    -0.06
    amient
    -0.06
    (SP
    -0.06
    POSITIVE LOGITS
    achel
    0.07
    itta
    0.06
    inar
    0.06
    -lnd
    0.06
    ix
    0.06
    iza
    0.06
    icia
    0.06
     numberWith
    0.06
    idor
    0.06
    asha
    0.05
    Activations Density 0.014%

    No Known Activations