Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 76473
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables used in scientific equations

    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
    ancock
    -0.07
    ÛĢ
    -0.07
    ksam
    -0.07
    ithe
    -0.07
    inel
    -0.06
    cil
    -0.06
    bei
    -0.06
    nesty
    -0.06
    .ie
    -0.06
    ément
    -0.06
    POSITIVE LOGITS
    922
    0.06
     MessageBoxButton
    0.06
    éļĨ
    0.06
     GUIStyle
    0.06
    972
    0.06
    \)
    0.06
    834
    0.06
     Hind
    0.06
     forb
    0.06
    uden
    0.06
    Activations Density 0.146%

    No Known Activations