© 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. 28893
    Prev
    Next
    INDEX
    Explanations

    words indicating concession or contrast

    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
    attles
    -0.07
     ev
    -0.06
    енко
    -0.06
     ont
    -0.06
     modifiers
    -0.06
    vide
    -0.06
     util
    -0.05
    164
    -0.05
     brutally
    -0.05
    issen
    -0.05
    POSITIVE LOGITS
    ignum
    0.08
    è¬Ŀ
    0.07
    IFn
    0.07
    izzo
    0.07
     bÃło
    0.07
     pathname
    0.07
    lek
    0.07
    NCY
    0.07
    è°¢
    0.07
     Woody
    0.07
    Activations Density 0.000%

    No Known Activations