© 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. 60766
    Prev
    Next
    INDEX
    Explanations

    expectations related to treatment and experiences

    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
    .Tool
    -0.08
     dán
    -0.07
    678
    -0.07
    ods
    -0.07
     Hib
    -0.07
    .docker
    -0.07
    æŁ
    -0.06
    ulton
    -0.06
    dock
    -0.06
    asil
    -0.06
    POSITIVE LOGITS
     approached
    0.06
     manner
    0.06
     handled
    0.06
    _handles
    0.06
    169
    0.06
     fashion
    0.06
    acob
    0.06
    et
    0.06
     обÑģÑĤ
    0.06
    lander
    0.06
    Activations Density 0.025%

    No Known Activations