© 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. 93579
    Prev
    Next
    INDEX
    Explanations

    references to entertainment companies and records

    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
    anes
    -0.07
    okt
    -0.06
    åĬ¿
    -0.06
     geme
    -0.06
    aris
    -0.06
     sứ
    -0.06
     Gibson
    -0.06
    efd
    -0.06
    unga
    -0.06
    oli
    -0.06
    POSITIVE LOGITS
    allee
    0.08
     Budd
    0.07
    ProcessEvent
    0.07
    оÑĢе
    0.07
    绾
    0.07
    azo
    0.07
     Prod
    0.06
    apiro
    0.06
    Ñıз
    0.06
    ntag
    0.06
    Activations Density 0.002%

    No Known Activations