© 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. 119422
    Prev
    Next
    INDEX
    Explanations

    terms related to hearing and hearing impairments

    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
    械
    -0.07
    AVE
    -0.07
    éİ®
    -0.07
    ials
    -0.07
    uplic
    -0.07
    cki
    -0.07
    UMMY
    -0.07
    gh
    -0.06
    owa
    -0.06
    _mk
    -0.06
    POSITIVE LOGITS
     loss
    0.09
     Loss
    0.07
     Fi
    0.06
     Burgess
    0.06
    lessness
    0.06
    -loss
    0.06
    oun
    0.06
     McCabe
    0.06
    lify
    0.06
     Burton
    0.06
    Activations Density 0.002%

    No Known Activations