© 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. 15-LLAMASCOPE-RES-131K
    11. 87486
    Prev
    Next
    INDEX
    Explanations

    phrases related to weight or burden

    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
    पत
    -0.08
    ourcem
    -0.08
     åĤ
    -0.07
     {{{
    -0.07
     Leban
    -0.07
    lage
    -0.07
    sterol
    -0.07
    è¾Ľ
    -0.06
    .codes
    -0.06
     yans
    -0.06
    POSITIVE LOGITS
     during
    0.06
     involving
    0.06
     approx
    0.06
     dur
    0.06
    olen
    0.06
     en
    0.06
     motor
    0.06
    (dc
    0.06
     dro
    0.06
     involve
    0.05
    Activations Density 0.000%

    No Known Activations