© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4097
    Prev
    Next
    INDEX
    Explanations

    specific nouns, especially in the context of artistic or cultural works

    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
    prene
    -0.06
    usch
    -0.06
     Dense
    -0.06
    oren
    -0.06
     br
    -0.06
     Weaver
    -0.05
     Completed
    -0.05
     поба
    -0.05
    ropical
    -0.05
    Sparse
    -0.05
    POSITIVE LOGITS
    mpar
    0.07
    unma
    0.07
    which
    0.07
    åħĥ
    0.06
     which
    0.06
    avou
    0.06
    lero
    0.06
    Ñĩем
    0.06
    orro
    0.06
    ä¸Ķ
    0.06
    Activations Density 0.021%

    No Known Activations