© 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. 4598
    Prev
    Next
    INDEX
    Explanations

    user interactions and comments in the document

    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
    oga
    -0.06
    raig
    -0.06
    armor
    -0.06
    ढ
    -0.06
    aksi
    -0.06
    aepernick
    -0.06
    oxel
    -0.06
     sür
    -0.06
    orp
    -0.06
     Churchill
    -0.06
    POSITIVE LOGITS
    emic
    0.07
    iosper
    0.07
    ionic
    0.07
    iffe
    0.06
    angered
    0.06
    isan
    0.06
     ev
    0.06
    urst
    0.06
     Rubin
    0.06
    azen
    0.06
    Activations Density 0.003%

    No Known Activations