© 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. 82781
    Prev
    Next
    INDEX
    Explanations

    terms related to deafness and sign language

    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
    grade
    -0.08
    Grade
    -0.06
    ç»ĩ
    -0.06
    缩
    -0.06
    -grade
    -0.06
    823
    -0.06
    IMA
    -0.06
     rum
    -0.06
    /rss
    -0.06
    \:
    -0.06
    POSITIVE LOGITS
     deaf
    0.10
     coch
    0.09
     signer
    0.08
     hearing
    0.07
     speech
    0.07
     signing
    0.07
     communic
    0.07
    peech
    0.07
     Hearing
    0.07
     Signing
    0.07
    Activations Density 0.011%

    No Known Activations