© 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. 9-LLAMASCOPE-RES-131K
    11. 95548
    Prev
    Next
    INDEX
    Explanations

    references to the country Azerbaijan

    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
    enda
    -0.07
    ip
    -0.07
    CV
    -0.07
    ew
    -0.06
    éra
    -0.06
    strand
    -0.06
    era
    -0.06
     Borg
    -0.06
    illiseconds
    -0.06
    ley
    -0.06
    POSITIVE LOGITS
    arem
    0.07
     Kent
    0.07
    errat
    0.07
    ehir
    0.07
    olina
    0.07
     huis
    0.06
    #ac
    0.06
    Ģ
    0.06
    jde
    0.06
    asive
    0.06
    Activations Density 0.001%

    No Known Activations