© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2685
    Prev
    Next
    INDEX
    Explanations

    references to people or groups involved in discussions or processes

    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
    Ïģεί
    -0.06
    rk
    -0.06
    олÑı
    -0.06
    isz
    -0.06
     Jew
    -0.06
    sled
    -0.06
    .observable
    -0.06
    ered
    -0.06
    rado
    -0.06
     Jelly
    -0.06
    POSITIVE LOGITS
     be
    0.07
    yster
    0.07
     haya
    0.06
    ichert
    0.06
    ovna
    0.06
     ready
    0.06
     read
    0.06
     bare
    0.06
    antas
    0.05
     happen
    0.05
    Activations Density 0.040%

    No Known Activations