© 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 EvalsExportsAPI 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. 71235
    Prev
    Next
    INDEX
    Explanations

    technical identifiers related to programming and system 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
    elo
    -0.06
    à¹Ħว
    -0.06
     quot
    -0.06
    RET
    -0.06
    abay
    -0.06
    ForKey
    -0.05
    &utm
    -0.05
    .Apis
    -0.05
    çļĦæĺ¯
    -0.05
    epar
    -0.05
    POSITIVE LOGITS
     actionTypes
    0.07
    ursive
    0.07
    okin
    0.07
     Ez
    0.06
    akk
    0.06
    ør
    0.06
     ActionTypes
    0.06
    ÑĨез
    0.06
    ÑĭÑĤ
    0.06
    icle
    0.06
    Activations Density 0.046%

    No Known Activations