© 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. 93127
    Prev
    Next
    INDEX
    Explanations

    phrases involving responses to questions or accusations

    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
    ì±Ħ
    -0.07
    iç
    -0.07
    ÑĢиз
    -0.07
    IKE
    -0.07
    lio
    -0.07
    иком
    -0.07
    .indices
    -0.07
     اÙĦرسÙħÙĬ
    -0.06
    pard
    -0.06
    Å¡nÃŃ
    -0.06
    POSITIVE LOGITS
     statement
    0.08
     claims
    0.07
    ycz
    0.07
    statement
    0.07
     recent
    0.07
    arih
    0.07
     colleague
    0.06
    ida
    0.06
     critics
    0.06
    ozem
    0.06
    Activations Density 0.018%

    No Known Activations