© 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. 93925
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Super" in various contexts

    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
    tik
    -0.08
    ahoma
    -0.08
    sla
    -0.08
    alon
    -0.07
    sel
    -0.07
    afari
    -0.07
    sburg
    -0.07
    borough
    -0.07
    ek
    -0.07
    rottle
    -0.07
    POSITIVE LOGITS
    ordinate
    0.10
    ieur
    0.09
    iors
    0.09
     Super
    0.09
    ior
    0.09
    IOR
    0.08
    Super
    0.07
    (super
    0.07
    intendent
    0.07
    stit
    0.07
    Activations Density 0.014%

    No Known Activations