© 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. 84087
    Prev
    Next
    INDEX
    Explanations

    references to specific software protocols and tools related to networking and security

    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
    ãģķãĤĵãģĮ
    -0.08
    ãģķãĤĵãģ®
    -0.07
    ora
    -0.07
     ç¤
    -0.07
    erial
    -0.06
    zelf
    -0.06
    ies
    -0.06
    راÙĨÙĩ
    -0.06
    reh
    -0.06
    ãģķãĤĵãģ¯
    -0.06
    POSITIVE LOGITS
    -enabled
    0.07
    vla
    0.07
    ://%
    0.07
    -equipped
    0.07
    åįıè®®
    0.07
    -using
    0.06
    YPE
    0.06
    ewing
    0.06
    <small
    0.06
    -based
    0.06
    Activations Density 0.077%

    No Known Activations