© 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. 105251
    Prev
    Next
    INDEX
    Explanations

    expressions of caution or awareness

    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
     (
    -0.06
     either
    -0.06
     el
    -0.06
     Bru
    -0.06
    stit
    -0.06
     Kir
    -0.06
     Ged
    -0.05
     pieces
    -0.05
    ï
    -0.05
    adj
    -0.05
    POSITIVE LOGITS
     bahwa
    0.09
    akis
    0.08
    ãĥ³ãĥĩ
    0.07
     rằng
    0.07
    .intellij
    0.07
    ÑĨа
    0.07
    anvas
    0.07
    otime
    0.07
    erdale
    0.07
    ationToken
    0.07
    Activations Density 0.010%

    No Known Activations