© 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. 93644
    Prev
    Next
    INDEX
    Explanations

    references to liquid measurements and packaging quantities

    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
    -0.07
    Drop
    -0.06
    kas
    -0.06
    hoo
    -0.06
     Dollar
    -0.05
     drop
    -0.05
    éĵ
    -0.05
    apiro
    -0.05
    eil
    -0.05
     dropped
    -0.05
    POSITIVE LOGITS
    stants
    0.08
    ìĶ©
    0.08
    (pack
    0.08
     pack
    0.07
    icontrol
    0.07
    okit
    0.07
    icont
    0.07
    ÃĹ↵↵
    0.07
     packs
    0.07
    conds
    0.07
    Activations Density 0.006%

    No Known Activations