© 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. 98151
    Prev
    Next
    INDEX
    Explanations

    data structures and elements related to programming or coding APIs

    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
    igo
    -0.07
    aper
    -0.06
    ctor
    -0.06
    eya
    -0.06
    xt
    -0.06
    qt
    -0.06
    aira
    -0.06
    ude
    -0.06
    vat
    -0.06
    assign
    -0.06
    POSITIVE LOGITS
    UnderTest
    0.08
    avenport
    0.07
    åĵ¡
    0.07
    üst
    0.07
    òi
    0.07
     вÑĭбÑĢа
    0.07
    ála
    0.07
    lyph
    0.07
    ertiary
    0.07
     olma
    0.07
    Activations Density 0.027%

    No Known Activations