© 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. 5399
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or strong emotional reactions

    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
    ings
    -0.09
    -quarters
    -0.08
    ful
    -0.08
    _OCCURRED
    -0.08
    ula
    -0.08
    ond
    -0.08
    fully
    -0.08
    аниÑĨ
    -0.07
    ild
    -0.07
    nt
    -0.07
    POSITIVE LOGITS
    !(
    0.07
    è¯Ŀ
    0.06
    -fast
    0.06
    cluded
    0.06
    alf
    0.06
    rå
    0.06
    ople
    0.06
    etwork
    0.06
    WD
    0.06
    -long
    0.06
    Activations Density 0.011%

    No Known Activations