© 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. 92473
    Prev
    Next
    INDEX
    Explanations

    geographical directional terms

    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
    ourg
    -0.06
    	Copyright
    -0.06
    	explicit
    -0.06
    سب
    -0.06
    usiness
    -0.06
    нам
    -0.06
    annis
    -0.06
     lineno
    -0.05
    ivicrm
    -0.05
    .flat
    -0.05
    POSITIVE LOGITS
    -side
    0.09
     end
    0.09
     side
    0.08
    side
    0.08
     portion
    0.07
     aspect
    0.07
    .scalablytyped
    0.07
    -end
    0.07
     edge
    0.07
    most
    0.07
    Activations Density 0.015%

    No Known Activations