© 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. 27048
    Prev
    Next
    INDEX
    Explanations

    nouns related to categorization and evaluation contexts

    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
    inch
    -0.06
    ameleon
    -0.06
    ÙıÙĨ
    -0.06
    ranÃŃ
    -0.06
    amber
    -0.06
    Ñĩем
    -0.06
    anan
    -0.06
    anse
    -0.06
     pÅĻev
    -0.06
    ανά
    -0.06
    POSITIVE LOGITS
    idel
    0.07
    uld
    0.06
    sterol
    0.06
     ëķĮ문
    0.06
    agogue
    0.06
    eking
    0.06
    namen
    0.06
     Vill
    0.06
    CU
    0.06
     reserve
    0.05
    Activations Density 0.000%

    No Known Activations