© 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. 26911
    Prev
    Next
    INDEX
    Explanations

    topics related to recognition and accomplishments

    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
    AYOUT
    -0.08
    esel
    -0.07
    enden
    -0.07
    viso
    -0.06
    uet
    -0.06
    ıma
    -0.06
    ardy
    -0.06
    OutOfBoundsException
    -0.06
    ään
    -0.06
    icket
    -0.06
    POSITIVE LOGITS
     everywhere
    0.13
     every
    0.10
     apl
    0.10
     gal
    0.09
    every
    0.08
     GAL
    0.08
     abound
    0.08
     Gal
    0.07
     numerous
    0.07
     almost
    0.07
    Activations Density 0.171%

    No Known Activations