© 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. 90108
    Prev
    Next
    INDEX
    Explanations

    references to specific video game titles and expansions

    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
    инг
    -0.08
    ä»Ļ
    -0.07
    ATALOG
    -0.07
    ESSAGES
    -0.06
    vore
    -0.06
     å®®
    -0.06
    .cx
    -0.06
    rtc
    -0.06
    ä½³
    -0.06
    áo
    -0.06
    POSITIVE LOGITS
     Edition
    0.09
     edition
    0.07
     Fist
    0.07
    otime
    0.06
    /register
    0.06
    ç¯ĩ
    0.06
     Stamp
    0.06
    236
    0.06
    umed
    0.05
    isode
    0.05
    Activations Density 0.022%

    No Known Activations