© 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. 75392
    Prev
    Next
    INDEX
    Explanations

    terms related to deception and concealment

    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
    तर
    -0.07
    ثاÙĦ
    -0.07
    .scalablytyped
    -0.07
    xis
    -0.07
    SpaceItem
    -0.07
    ImageContext
    -0.07
    aze
    -0.07
    assage
    -0.07
    ิà¸ķ
    -0.07
    perature
    -0.07
    POSITIVE LOGITS
    ously
    0.09
    ingly
    0.07
    ory
    0.07
    ively
    0.06
    y
    0.06
    gow
    0.06
     cover
    0.06
    ous
    0.06
    ably
    0.06
     mas
    0.06
    Activations Density 0.006%

    No Known Activations