© 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. 59195
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to bowing or showing reverence

    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
    icari
    -0.08
    culus
    -0.07
    reeze
    -0.07
    CEPT
    -0.07
     systemd
    -0.07
    afone
    -0.07
    lag
    -0.07
    ssc
    -0.07
    apter
    -0.07
    mdp
    -0.07
    POSITIVE LOGITS
    ault
    0.07
     Syndrome
    0.06
     bend
    0.06
     Bent
    0.06
     bent
    0.06
     bending
    0.06
     Bend
    0.06
     syndrome
    0.06
    elt
    0.06
     genu
    0.06
    Activations Density 0.009%

    No Known Activations