© 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. 2588
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and product effectiveness

    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
     might
    -0.07
     KO
    -0.06
     Dash
    -0.06
    Enlarge
    -0.06
    some
    -0.06
     plenty
    -0.06
    Dash
    -0.06
     oneself
    -0.06
     Experiment
    -0.05
     èµ·
    -0.05
    POSITIVE LOGITS
     unlike
    0.12
     Unlike
    0.10
    Unlike
    0.10
     UNIQUE
    0.09
     patented
    0.09
     unique
    0.08
     revolutionary
    0.08
    revolution
    0.08
     revolution
    0.07
    Unique
    0.07
    Activations Density 0.028%

    No Known Activations