© 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. 15182
    Prev
    Next
    INDEX
    Explanations

    CSS styling attributes and properties

    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
    práv
    -0.08
    иÑĩа
    -0.08
    ÄĽtÃŃ
    -0.07
    inch
    -0.07
    .kotlin
    -0.07
    reu
    -0.07
    loth
    -0.07
    gili
    -0.07
    podob
    -0.07
    _ble
    -0.07
    POSITIVE LOGITS
    ailable
    0.07
    ;↵
    0.06
     Cortex
    0.06
    .Euler
    0.06
    _TAC
    0.06
    -пÑĢав
    0.06
    ãĤ¿ãĥ¼
    0.06
     unp
    0.06
    =yes
    0.06
    adir
    0.06
    Activations Density 0.016%

    No Known Activations