© 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. 108579
    Prev
    Next
    INDEX
    Explanations

    expressions of pride or quality in service or accomplishment

    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
    окол
    -0.07
     Grave
    -0.06
    ibar
    -0.06
    inges
    -0.06
     Carm
    -0.06
    ailles
    -0.06
    VERR
    -0.06
     Represent
    -0.06
    inne
    -0.06
    erson
    -0.05
    POSITIVE LOGITS
     ourselves
    0.08
    .glide
    0.07
     itself
    0.07
    åĩºåĵģ
    0.07
    .tintColor
    0.07
     sobie
    0.07
    ÏĦαι
    0.07
    .UIManager
    0.07
    antly
    0.06
    .trip
    0.06
    Activations Density 0.001%

    No Known Activations