© 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. 90048
    Prev
    Next
    INDEX
    Explanations

    numerical values related to mathematical functions or properties

    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
    illac
    -0.07
    át
    -0.07
     [âĢ¦]↵↵
    -0.07
     >č↵
    -0.07
    ville
    -0.07
    ObjectOfType
    -0.07
    й
    -0.07
    سÙĨÚ¯
    -0.07
    GenerationStrategy
    -0.07
    تاب
    -0.07
    POSITIVE LOGITS
    lx
    0.07
     erm
    0.07
    ,
    0.06
     S
    0.06
     scre
    0.06
     [
    0.06
    ather
    0.06
    EEDED
    0.06
     gro
    0.06
     Mike
    0.06
    Activations Density 0.006%

    No Known Activations