© 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. 117525
    Prev
    Next
    INDEX
    Explanations

    information related to hotel amenities and services

    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
     ê²ĥëıĦ
    -0.06
    stp
    -0.06
    ÑģÑĤÑĮ
    -0.05
    سÙĩ
    -0.05
    urname
    -0.05
    rate
    -0.05
     spite
    -0.05
     Burnett
    -0.05
    /Form
    -0.05
     ë¹Ħ
    -0.05
    POSITIVE LOGITS
     answer
    0.10
     answered
    0.09
     Answer
    0.07
     ANSW
    0.07
    .scalablytyped
    0.07
     çŃĶ
    0.07
    .define
    0.07
    ode
    0.07
    Ans
    0.07
    answer
    0.07
    Activations Density 0.011%

    No Known Activations