© 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. 73224
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the extent or degree of involvement

    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
    thus
    -0.07
    owler
    -0.06
    ogene
    -0.06
    ellig
    -0.06
    nej
    -0.06
    renc
    -0.06
    egr
    -0.06
    iger
    -0.06
    inte
    -0.05
    inkel
    -0.05
    POSITIVE LOGITS
     because
    0.19
    because
    0.16
     porque
    0.15
     Because
    0.14
    Because
    0.14
    ecause
    0.14
    åĽłä¸º
    0.13
     karena
    0.13
     parce
    0.12
     omdat
    0.12
    Activations Density 0.012%

    No Known Activations