© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1568
    Prev
    Next
    INDEX
    Explanations

    phrases related to concealment or hidden aspects

    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
     Suspension
    -0.08
    czy
    -0.08
     suspension
    -0.08
    wl
    -0.07
     suspended
    -0.07
     дело
    -0.07
    Susp
    -0.07
    vfs
    -0.07
    خر
    -0.07
    ÐĴС
    -0.07
    POSITIVE LOGITS
     hiding
    0.12
     hide
    0.11
     hidden
    0.11
     hid
    0.11
     hides
    0.11
     behind
    0.10
    èĹı
    0.10
    -hidden
    0.10
    éļIJèĹı
    0.09
    .hide
    0.09
    Activations Density 0.026%

    No Known Activations