© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    references to musical single releases and collaborations

    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
    .tel
    -0.06
    entai
    -0.06
    xae
    -0.06
    urum
    -0.06
    RIX
    -0.06
    ÑĢоÑİ
    -0.06
     locally
    -0.06
    alties
    -0.06
    æµħ
    -0.06
     Ñĥв
    -0.06
    POSITIVE LOGITS
    -prepend
    0.07
    Ế
    0.07
     publishing
    0.07
    à¹Ģà¸ĭà¸Ńร
    0.07
    announce
    0.07
    åıijå¸ĥ
    0.06
    ón
    0.06
    ħn
    0.06
     leaking
    0.06
     surprise
    0.06
    Activations Density 0.019%

    No Known Activations