© 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 EvalsExportsAPI 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. 77315
    Prev
    Next
    INDEX
    Explanations

    references to audience interaction and feedback

    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
     sou
    -0.06
    Thomas
    -0.06
    ¤
    -0.06
     Wang
    -0.06
     Thomas
    -0.06
     Ritch
    -0.06
    uda
    -0.06
     Reynolds
    -0.06
    ahy
    -0.05
    ha
    -0.05
    POSITIVE LOGITS
     episode
    0.10
     Episode
    0.09
    Episode
    0.08
    .gdx
    0.08
    episode
    0.08
    Callbacks
    0.08
     hosts
    0.07
    iode
    0.07
    adero
    0.07
     episodes
    0.07
    Activations Density 0.005%

    No Known Activations