© 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. 9-LLAMASCOPE-RES-131K
    11. 94647
    Prev
    Next
    INDEX
    Explanations

    technical language related to functions and parameters in programming or algorithms

    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
    apr
    -0.07
    esub
    -0.07
    空
    -0.07
    å¹³
    -0.06
    imedia
    -0.06
    spb
    -0.06
    445
    -0.06
     NGX
    -0.06
    .scalablytyped
    -0.06
    .Fat
    -0.06
    POSITIVE LOGITS
    stands
    0.07
    üst
    0.06
    shade
    0.06
    reesome
    0.06
    ĭ
    0.06
    ragen
    0.06
    ente
    0.06
     ent
    0.06
    ster
    0.06
     unpack
    0.06
    Activations Density 0.113%

    No Known Activations