© 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. 18356
    Prev
    Next
    INDEX
    Explanations

    phrases related to recognition or attribution of contributions

    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
    er
    -0.08
    ucha
    -0.07
    eil
    -0.07
    isme
    -0.06
    flies
    -0.06
     ropes
    -0.06
    erin
    -0.06
    -notification
    -0.06
    orf
    -0.06
     bred
    -0.06
    POSITIVE LOGITS
    бов
    0.07
    DAC
    0.06
     Tir
    0.06
    ç½²
    0.06
     creation
    0.06
    istar
    0.06
     tá»Ń
    0.06
    ÑĤом
    0.06
     attributes
    0.06
     credit
    0.06
    Activations Density 0.002%

    No Known Activations