© 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. 17-LLAMASCOPE-RES-131K
    11. 17898
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to relationships and community engagement

    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
    zion
    -0.07
    437
    -0.07
    ongo
    -0.06
    ÂŃs
    -0.06
    amax
    -0.06
    /copyleft
    -0.06
    ÂŃi
    -0.06
    istrovstvÃŃ
    -0.06
    bÃŃ
    -0.06
    781
    -0.06
    POSITIVE LOGITS
    ÌĨ
    0.09
    Äĩi
    0.08
    hd
    0.07
    ãĤĵ
    0.07
    Ì
    0.06
    sic
    0.06
    ients
    0.06
    ãĥ³ãĥĨãĤ£
    0.06
    ÑĪов
    0.06
    дÑı
    0.06
    Activations Density 0.199%

    No Known Activations