© 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. 9-LLAMASCOPE-RES-131K
    11. 98124
    Prev
    Next
    INDEX
    Explanations

    mythological creatures and entities

    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
    ToWorld
    -0.07
    ethe
    -0.07
     extrad
    -0.07
    ihan
    -0.07
    SimpleName
    -0.07
    ends
    -0.06
    agan
    -0.06
    219
    -0.06
    chez
    -0.06
    yy
    -0.06
    POSITIVE LOGITS
     Bros
    0.06
    úp
    0.06
     mythical
    0.06
    çŀ
    0.06
    Toolbar
    0.06
    žen
    0.06
    -toolbar
    0.06
    buster
    0.06
    INF
    0.05
    ovich
    0.05
    Activations Density 0.003%

    No Known Activations