© 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. 55914
    Prev
    Next
    INDEX
    Explanations

    connections to locations and identities in investigative 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
    ̣
    -0.07
    aar
    -0.06
     spin
    -0.06
    iones
    -0.06
    redicate
    -0.06
    ÙĪÛĮÙĨت
    -0.06
    ürk
    -0.06
    rer
    -0.05
    iye
    -0.05
    semicolon
    -0.05
    POSITIVE LOGITS
    ÏĥÏĦÏĮ
    0.07
    uts
    0.07
    igi
    0.06
    ately
    0.06
    uling
    0.06
    anza
    0.06
    ëĭĪìķĦ
    0.06
    bid
    0.06
    UT
    0.06
    etta
    0.06
    Activations Density 0.006%

    No Known Activations