© 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. 121302
    Prev
    Next
    INDEX
    Explanations

    terms related to usefulness and improvement in service or product quality

    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
     Tucker
    -0.06
    929
    -0.06
    amac
    -0.06
    398
    -0.06
    rist
    -0.06
    atura
    -0.06
    cast
    -0.06
    _VARS
    -0.06
    omer
    -0.06
    adies
    -0.06
    POSITIVE LOGITS
    EMY
    0.07
    sse
    0.07
     Frank
    0.07
    าà¸ĺ
    0.07
     frank
    0.07
    ozem
    0.06
    azel
    0.06
    Truthy
    0.06
    꾸
    0.06
     vag
    0.06
    Activations Density 0.001%

    No Known Activations