© 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 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. 29199
    Prev
    Next
    INDEX
    Explanations

    references to "secrets" and their implications in various contexts

    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
    SSIP
    -0.07
    лаб
    -0.07
    alon
    -0.07
    ITA
    -0.07
    aan
    -0.07
    itas
    -0.06
    abus
    -0.06
    clr
    -0.06
    .struts
    -0.06
    æ¦
    -0.06
    POSITIVE LOGITS
     secrets
    0.13
     secret
    0.12
     Secrets
    0.12
     Secret
    0.10
    Secret
    0.09
    -secret
    0.09
    (secret
    0.08
    secret
    0.08
     Successful
    0.08
    ç§ĺ
    0.08
    Activations Density 0.011%

    No Known Activations