© 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. 5-LLAMASCOPE-RES-131K
    11. 125941
    Prev
    Next
    INDEX
    Explanations

    mentions of global businesses or organizations

    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
    \Id
    -0.07
    ANJI
    -0.06
    ä¿
    -0.06
    074
    -0.06
    ÑģÑĥÑĤ
    -0.06
    íĥľ
    -0.06
    ilar
    -0.06
    Ø´ÙħاÙĦÛĮ
    -0.06
    psilon
    -0.06
    errer
    -0.06
    POSITIVE LOGITS
    ders
    0.07
    dal
    0.07
    åĦĢ
    0.06
    rado
    0.06
    ź
    0.06
    ınca
    0.06
    å´İ
    0.06
    marshall
    0.06
    ergus
    0.06
     tslib
    0.06
    Activations Density 0.000%

    No Known Activations