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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75290
    Prev
    Next
    INDEX
    Explanations

    instances of comparisons or contrasts between different subjects or ideas

    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
    ãģķãĤī
    -0.09
    zim
    -0.07
    lıģının
    -0.07
     yetiÅŁ
    -0.07
    erson
    -0.07
    åIJĮ
    -0.06
    sep
    -0.06
    Ùĥس
    -0.06
    ÏĥÏĦα
    -0.06
     Noticed
    -0.06
    POSITIVE LOGITS
     contrast
    0.06
    achts
    0.06
    adratic
    0.06
    iyim
    0.06
    ingly
    0.06
    ivism
    0.06
     Fat
    0.06
    OLDER
    0.06
    uess
    0.06
    wise
    0.06
    Activations Density 0.006%

    No Known Activations