© 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. 15-LLAMASCOPE-RES-131K
    11. 1182
    Prev
    Next
    INDEX
    Explanations

    phrases related to the transmission and effects of contaminants or medications

    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
    utor
    -0.06
    ense
    -0.06
    ाà¤Ĺत
    -0.06
    rim
    -0.06
     alignment
    -0.06
     alignments
    -0.06
    ogg
    -0.06
     rumor
    -0.06
     saving
    -0.06
     starting
    -0.05
    POSITIVE LOGITS
    ckt
    0.09
    RELEASE
    0.07
     æ¿
    0.07
    antha
    0.07
    elize
    0.07
     fisse
    0.06
    rets
    0.06
    bast
    0.06
    ichen
    0.06
    ovky
    0.06
    Activations Density 0.012%

    No Known Activations