© 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. 1634
    Prev
    Next
    INDEX
    Explanations

    references to decision-making authority in military or organizational 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
     itself
    -0.13
     its
    -0.09
     Its
    -0.08
    Its
    -0.07
    (es
    -0.07
     коÑĤоÑĢое
    -0.07
    åıĬåħ¶
    -0.07
    odge
    -0.06
     оно
    -0.06
    ersist
    -0.06
    POSITIVE LOGITS
    alic
    0.08
     are
    0.07
    omba
    0.07
    zia
    0.07
     themselves
    0.07
    alon
    0.07
    OAD
    0.07
    linger
    0.07
    tails
    0.07
    ÃŃr
    0.07
    Activations Density 0.049%

    No Known Activations