© 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 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. 106200
    Prev
    Next
    INDEX
    Explanations

    references to organizations, companies, or groups involved in various activities

    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
    makt
    -0.09
    ãģĵãģĿ
    -0.09
    jedn
    -0.08
    ãĥĥãĥĦ
    -0.08
     gerek
    -0.08
    bsite
    -0.08
    //{{
    -0.08
    anter
    -0.08
    Sharper
    -0.08
    алеж
    -0.07
    POSITIVE LOGITS
     decided
    0.09
     now
    0.07
     took
    0.07
     finally
    0.07
     suddenly
    0.07
     decide
    0.07
     became
    0.07
     opt
    0.06
     team
    0.06
    1
    0.06
    Activations Density 0.067%

    No Known Activations