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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 77407
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or actions that occur in secret or without public knowledge

    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
    orda
    -0.07
    bery
    -0.07
    .apps
    -0.07
     اÙĦس
    -0.07
     DisplayName
    -0.07
    forgot
    -0.06
    displayName
    -0.06
    æĩ
    -0.06
    owitz
    -0.06
    ActionCreators
    -0.06
    POSITIVE LOGITS
     closed
    0.10
     Closed
    0.09
     behind
    0.09
     scenes
    0.08
    Closed
    0.08
    closed
    0.08
     doors
    0.08
     Behind
    0.07
     CLOSED
    0.07
     walls
    0.07
    Activations Density 0.006%

    No Known Activations