© 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. 15-LLAMASCOPE-RES-131K
    11. 87075
    Prev
    Next
    INDEX
    Explanations

    discussions about college football bowl eligibility criteria

    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
    eyse
    -0.08
     AsyncCallback
    -0.07
    bsolute
    -0.06
     záv
    -0.06
    æk
    -0.06
    uisse
    -0.06
    _QMARK
    -0.06
    eview
    -0.06
     chall
    -0.06
     observational
    -0.06
    POSITIVE LOGITS
    jem
    0.08
    heed
    0.07
    HEME
    0.06
    prak
    0.06
    ubbles
    0.06
    ject
    0.06
    pell
    0.06
    ilig
    0.06
    mlink
    0.05
     fourth
    0.05
    Activations Density 0.003%

    No Known Activations