© 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. 42074
    Prev
    Next
    INDEX
    Explanations

    phrases related to luck and performance in sports

    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
     myself
    -0.06
     Rad
    -0.06
    ikel
    -0.06
    cha
    -0.06
     actually
    -0.06
     (
    -0.05
    ottes
    -0.05
     Econom
    -0.05
     radial
    -0.05
    aval
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.08
    chyb
    0.07
    your
    0.07
    ZeroWidthSpace
    0.07
    QRST
    0.07
     dostan
    0.07
     your
    0.07
    yla
    0.07
    aylight
    0.07
    æ©Ł
    0.07
    Activations Density 0.030%

    No Known Activations