© 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. 17-LLAMASCOPE-RES-131K
    11. 74389
    Prev
    Next
    INDEX
    Explanations

    words related to concealment or hiding

    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
    stras
    -0.08
    ello
    -0.07
    yp
    -0.07
    sembled
    -0.07
    lator
    -0.07
    eer
    -0.07
    CHANT
    -0.07
    ieved
    -0.07
    ائر
    -0.07
    lando
    -0.06
    POSITIVE LOGITS
    away
    0.09
    /show
    0.09
    ous
    0.08
    ously
    0.07
    rance
    0.07
    angu
    0.07
    -away
    0.07
    aways
    0.07
    ights
    0.07
    gger
    0.06
    Activations Density 0.014%

    No Known Activations