© 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. 53725
    Prev
    Next
    INDEX
    Explanations

    expressions of increasing intensity or accumulation in thoughts and actions

    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
    rst
    -0.07
    itest
    -0.06
    uki
    -0.06
    antis
    -0.06
    quent
    -0.06
    archives
    -0.06
    /cop
    -0.06
    whereIn
    -0.06
     your
    -0.06
     secs
    -0.06
    POSITIVE LOGITS
    è¶Ĭ
    0.09
     increasingly
    0.08
    bery
    0.07
     seemed
    0.07
    wu
    0.07
     seems
    0.07
    759
    0.07
    enance
    0.07
    -growing
    0.07
    åıĺå¾Ĺ
    0.06
    Activations Density 0.007%

    No Known Activations