© 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 EvalsExportsAPI 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. 119347
    Prev
    Next
    INDEX
    Explanations

    specific trademarks or names associated with products or entities

    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
    rtle
    -0.07
    ares
    -0.06
    orta
    -0.06
    cript
    -0.06
    unda
    -0.06
    иÑģÑĤ
    -0.06
    letal
    -0.06
    ired
    -0.06
    ext
    -0.06
    urname
    -0.06
    POSITIVE LOGITS
     Tro
    0.07
     tro
    0.07
    oux
    0.07
    UBLE
    0.07
    Tro
    0.07
    ppo
    0.07
    adero
    0.07
     Trou
    0.06
    ehler
    0.06
     Glover
    0.06
    Activations Density 0.015%

    No Known Activations