© 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. 79760
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions

    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
     kles
    -0.08
    گاÙĨ
    -0.07
    straint
    -0.07
    ahat
    -0.07
    oday
    -0.07
    .scalablytyped
    -0.07
    aneous
    -0.07
    rana
    -0.07
    à¹Ħว
    -0.07
    avana
    -0.07
    POSITIVE LOGITS
    ãĥĥãĥĪ
    0.07
    shan
    0.06
    401
    0.06
    133
    0.05
     fest
    0.05
    opt
    0.05
    olor
    0.05
    uster
    0.05
     stick
    0.05
    318
    0.05
    Activations Density 0.006%

    No Known Activations