© 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. 90011
    Prev
    Next
    INDEX
    Explanations

    brackets and certain types of punctuation in legal contexts

    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
    殿
    -0.07
    สล
    -0.07
    ##_
    -0.07
    okt
    -0.07
    iac
    -0.07
    ÙĬÙĦا
    -0.06
    itos
    -0.06
    бÑĥдÑĮ
    -0.06
    aar
    -0.06
    оÑĢоз
    -0.06
    POSITIVE LOGITS
    anzi
    0.07
     mey
    0.06
    enty
    0.06
     Bowman
    0.06
    getDisplay
    0.06
     Ferrari
    0.06
    eks
    0.05
    omm
    0.05
     Platt
    0.05
     liner
    0.05
    Activations Density 0.001%

    No Known Activations