© 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. 130267
    Prev
    Next
    INDEX
    Explanations

    components or structures associated with programming or mathematical expressions

    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
    ey
    -0.07
    immel
    -0.07
    agh
    -0.06
    344
    -0.06
     '\''
    -0.06
    io
    -0.06
    uro
    -0.06
    iga
    -0.06
    366
    -0.06
    ABCDEFG
    -0.06
    POSITIVE LOGITS
    kaar
    0.07
    oyo
    0.07
     another
    0.06
    zew
    0.06
    lements
    0.06
    .Assembly
    0.06
    èm
    0.06
    icontrol
    0.06
    nah
    0.06
     thems
    0.06
    Activations Density 0.115%

    No Known Activations