© 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. 39143
    Prev
    Next
    INDEX
    Explanations

    discussions about societal problems and accountability

    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
     vag
    -0.06
    eru
    -0.06
     equ
    -0.06
    olah
    -0.06
    stab
    -0.06
    ãĥ³ãĥĩ
    -0.06
    oho
    -0.06
    escort
    -0.06
    å´İ
    -0.06
    ridge
    -0.06
    POSITIVE LOGITS
     problem
    0.23
     Problem
    0.20
    problem
    0.20
    Problem
    0.18
    _problem
    0.17
     problema
    0.16
    .problem
    0.15
     proble
    0.15
    éĹ®é¢ĺ
    0.14
     problems
    0.14
    Activations Density 0.049%

    No Known Activations