© 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. 105927
    Prev
    Next
    INDEX
    Explanations

    medical terms and topics related to infections and imaging

    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
    bjerg
    -0.07
     åį
    -0.06
    wer
    -0.06
     Kemp
    -0.06
    chts
    -0.06
     explanatory
    -0.06
    WER
    -0.06
    ully
    -0.06
     island
    -0.06
    tg
    -0.06
    POSITIVE LOGITS
    ÏĦαι
    0.08
    ç«ł
    0.08
     Synd
    0.07
    znik
    0.07
    pez
    0.07
    onica
    0.07
    ipa
    0.06
    ãĥ¼ãĥ
    0.06
    ownik
    0.06
     synd
    0.06
    Activations Density 0.040%

    No Known Activations