© 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. 15-LLAMASCOPE-RES-131K
    11. 1204
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or alternatives

    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
    uur
    -0.06
    ol
    -0.06
     alone
    -0.06
     rather
    -0.05
     something
    -0.05
     otherwise
    -0.05
    aira
    -0.05
    issen
    -0.05
    zi
    -0.05
    ia
    -0.05
    POSITIVE LOGITS
     equally
    0.08
     similarly
    0.08
    òi
    0.08
    AUSE
    0.08
    że
    0.08
     ìĹŃìĭľ
    0.08
    ếu
    0.08
    /Dk
    0.07
    ¦æĥħ
    0.07
    erdem
    0.07
    Activations Density 0.020%

    No Known Activations