© 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. 87411
    Prev
    Next
    INDEX
    Explanations

    conditional and situational statements relating to actions or events

    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
    lez
    -0.07
     ÙĪاÙĦتÙĬ
    -0.07
    кап
    -0.07
     Král
    -0.07
    alars
    -0.07
    LAG
    -0.07
    Ùĩار
    -0.07
    каÑģ
    -0.07
    YPE
    -0.07
    iola
    -0.07
    POSITIVE LOGITS
    utral
    0.06
     Pty
    0.06
    uong
    0.06
     and
    0.06
     but
    0.06
    558
    0.05
    Äı
    0.05
    acky
    0.05
    иÑĢа
    0.05
     ng
    0.05
    Activations Density 0.071%

    No Known Activations