© 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. 17-LLAMASCOPE-RES-131K
    11. 58339
    Prev
    Next
    INDEX
    Explanations

    indications of academic achievement and commitment to education

    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
    ncmp
    -0.08
    ÏĥÏĢ
    -0.08
    itta
    -0.07
    retain
    -0.07
    vál
    -0.07
    _asm
    -0.07
    eid
    -0.07
    alance
    -0.07
    azzi
    -0.07
     ÐĴлади
    -0.07
    POSITIVE LOGITS
     promise
    0.07
     promising
    0.07
     likely
    0.07
     reasonably
    0.06
     compatible
    0.06
     likelihood
    0.06
     comm
    0.06
     Reason
    0.06
     promises
    0.06
    .promise
    0.06
    Activations Density 0.012%

    No Known Activations