© 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. 92287
    Prev
    Next
    INDEX
    Explanations

    phrases indicating purpose or reason

    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
    esis
    -0.07
    895
    -0.06
    HA
    -0.06
    ha
    -0.06
    ees
    -0.06
    agt
    -0.05
    ag
    -0.05
     vis
    -0.05
    699
    -0.05
    -ln
    -0.05
    POSITIVE LOGITS
    ascar
    0.08
    bidden
    0.08
    ÙĪجÙĩ
    0.08
    жа
    0.07
    ween
    0.07
    ãģ¹
    0.07
     purposes
    0.07
    gunta
    0.06
    ertino
    0.06
    neys
    0.06
    Activations Density 0.036%

    No Known Activations