© 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. 86991
    Prev
    Next
    INDEX
    Explanations

    terms related to information dissemination and communication

    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
    erras
    -0.08
    angle
    -0.08
    ilet
    -0.08
    ANA
    -0.07
    LER
    -0.07
    apis
    -0.07
    illard
    -0.07
    APA
    -0.07
    acher
    -0.07
    zano
    -0.07
    POSITIVE LOGITS
    ally
    0.09
    atics
    0.08
    ative
    0.07
    idable
    0.06
    449
    0.06
    ercial
    0.06
    ants
    0.06
    acje
    0.06
    ict
    0.06
    edly
    0.06
    Activations Density 0.020%

    No Known Activations