© 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. 29519
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or functionality

    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
     EÅŁ
    -0.07
    μμ
    -0.06
    аÑĢод
    -0.06
     ÙĪرزشÛĮ
    -0.06
     ì²ĺ
    -0.05
    Ļ¨
    -0.05
    393
    -0.05
     chaining
    -0.05
     unchanged
    -0.05
     odpad
    -0.05
    POSITIVE LOGITS
    òng
    0.07
    asser
    0.07
     purposes
    0.07
     Emerald
    0.07
    ény
    0.07
     purpose
    0.06
    aign
    0.06
    ung
    0.06
    ings
    0.06
    utter
    0.06
    Activations Density 0.026%

    No Known Activations