© 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. 56135
    Prev
    Next
    INDEX
    Explanations

    HTML or XML structural elements

    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
    alls
    -0.06
     Rig
    -0.05
    ÛĮÚ©ÛĮ
    -0.05
     wrapping
    -0.05
     Express
    -0.05
     Trace
    -0.05
    -e
    -0.05
    synthesize
    -0.05
    >.</
    -0.05
    -A
    -0.05
    POSITIVE LOGITS
    usp
    0.08
    alink
    0.08
    erais
    0.07
    rol
    0.07
     ÑģмоÑĤ
    0.07
    gam
    0.07
    tbody
    0.07
    ãĥį
    0.07
    -haspopup
    0.07
    asley
    0.07
    Activations Density 0.005%

    No Known Activations