© 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. 80150
    Prev
    Next
    INDEX
    Explanations

    error codes and status messages related to software crashes or failures

    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
     Minds
    -0.07
    ENCH
    -0.07
    enson
    -0.07
    à¹Īาย
    -0.07
    VERSE
    -0.07
    arya
    -0.06
     неп
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    Ñĥли
    -0.06
    grass
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.07
    //{{
    0.07
    erty
    0.07
    ioni
    0.06
    ound
    0.06
    .self
    0.06
    sgi
    0.06
    quam
    0.06
    gesi
    0.06
    éļĨ
    0.06
    Activations Density 0.001%

    No Known Activations