© 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. 74980
    Prev
    Next
    INDEX
    Explanations

    programming and computational language elements, particularly those related to functions and objects

    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
    ãĤ¤ãĥ¤
    -0.09
    ÐłÐĿ
    -0.08
     undermin
    -0.08
    interop
    -0.08
    iteli
    -0.08
    олож
    -0.08
    .Undef
    -0.08
    ctp
    -0.08
    CreateInfo
    -0.08
    à¹ĩà¸ķาม
    -0.08
    POSITIVE LOGITS
    o
    0.07
    us
    0.07
    z
    0.06
    ¿
    0.06
    x
    0.06
    ic
    0.06
    X
    0.06
    ¸
    0.06
    C
    0.06
    j
    0.06
    Activations Density 0.324%

    No Known Activations