© 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. 121225
    Prev
    Next
    INDEX
    Explanations

    Assertions and claims that begin with "surely."

    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
    orrh
    -0.07
    imen
    -0.07
    869
    -0.07
    erli
    -0.07
    ese
    -0.07
    quito
    -0.07
    oret
    -0.07
     realmente
    -0.07
    ray
    -0.07
    ugg
    -0.07
    POSITIVE LOGITS
    ance
    0.08
     enough
    0.07
    ments
    0.07
    ously
    0.07
    aptop
    0.07
     surely
    0.07
    lich
    0.06
    forth
    0.06
     not
    0.06
     rằng
    0.06
    Activations Density 0.005%

    No Known Activations