© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53966
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to method overriding

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ll
    -0.07
    olie
    -0.07
    ön
    -0.06
    165
    -0.06
    oret
    -0.06
    zin
    -0.06
     derby
    -0.06
    ngine
    -0.06
    äºĭæĥħ
    -0.06
     sut
    -0.05
    POSITIVE LOGITS
     void
    0.09
    mium
    0.08
    void
    0.08
    otch
    0.07
    otp
    0.07
    ANDOM
    0.07
    IFS
    0.07
    ήν
    0.07
    574
    0.07
    icorn
    0.07
    Activations Density 0.000%

    No Known Activations