© 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. 16156
    Prev
    Next
    INDEX
    Explanations

    Terms related to political or social events and their implications

    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
    BY
    -0.06
    å®ļ
    -0.06
    ead
    -0.06
     gem
    -0.06
    bou
    -0.06
     bou
    -0.06
    mÄĽ
    -0.06
    ushman
    -0.06
     Bu
    -0.06
    rada
    -0.06
    POSITIVE LOGITS
     indem
    0.17
     пÑĥÑĤем
    0.16
     ÑĪлÑıÑħом
    0.14
     bằng
    0.13
     tÃŃm
    0.12
     by
    0.11
     thanks
    0.10
     à¹Ĥà¸Ķย
    0.09
     mediante
    0.09
     grâce
    0.08
    Activations Density 0.554%

    No Known Activations