© 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. 129197
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs indicating quality or condition

    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
    esin
    -0.08
    onso
    -0.08
    olec
    -0.07
    agina
    -0.07
     ê°Ģì§Ģê³ł
    -0.06
    esis
    -0.06
    agner
    -0.06
    ÄĽlÃŃ
    -0.06
     Fucking
    -0.06
    alion
    -0.06
    POSITIVE LOGITS
     جاÙĨ
    0.07
    ''↵
    0.06
    ály
    0.06
    /extensions
    0.06
     lett
    0.06
     ÙĦÙĢ
    0.06
    /Foundation
    0.06
     probs
    0.06
    upo
    0.06
     reportedly
    0.05
    Activations Density 0.002%

    No Known Activations