© 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. 84361
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives describing frequency or state

    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
    ught
    -0.07
    annis
    -0.06
    itu
    -0.06
    oret
    -0.06
     dut
    -0.06
    kening
    -0.06
     succes
    -0.06
     via
    -0.06
    uren
    -0.06
    ammen
    -0.05
    POSITIVE LOGITS
     undecided
    0.07
    нима
    0.07
    हल
    0.07
    enant
    0.07
    jÃŃ
    0.07
     åı·
    0.06
     schö
    0.06
    imoto
    0.06
     nouve
    0.06
    оÑıÑĤ
    0.06
    Activations Density 0.001%

    No Known Activations