© 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. 120734
    Prev
    Next
    INDEX
    Explanations

    references to interviews and conversations in political contexts

    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
     hind
    -0.06
     convers
    -0.06
    Hint
    -0.05
     detriment
    -0.05
    202
    -0.05
     nor
    -0.05
     Hint
    -0.05
     inn
    -0.05
     chosen
    -0.05
    hind
    -0.05
    POSITIVE LOGITS
    Yesterday
    0.09
    æĺ¨
    0.09
     yesterday
    0.09
     tonight
    0.08
     Yesterday
    0.08
    ÅĻÃŃzenÃŃ
    0.08
    today
    0.08
    alama
    0.07
     tomorrow
    0.07
    esterday
    0.07
    Activations Density 0.051%

    No Known Activations