© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87815
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to programming and code execution

    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
     unl
    -0.07
    /Dk
    -0.07
    awe
    -0.06
    á»Ļ
    -0.06
     Haram
    -0.06
     avent
    -0.06
    amine
    -0.06
    abyrinth
    -0.06
    rios
    -0.06
    afil
    -0.06
    POSITIVE LOGITS
    Ī
    0.09
    alse
    0.08
    tsy
    0.07
    iants
    0.07
    elpers
    0.07
    ammers
    0.06
    æ´¥
    0.06
    ilingual
    0.06
    inth
    0.06
     skb
    0.06
    Activations Density 0.055%

    No Known Activations