© 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. 76306
    Prev
    Next
    INDEX
    Explanations

    phrases related to accusations and claims of wrongdoing

    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
    ENO
    -0.08
    ¶Į
    -0.07
    ijd
    -0.07
    uxtap
    -0.07
    ounter
    -0.07
    reff
    -0.07
    isOk
    -0.07
    дам
    -0.07
    áj
    -0.07
    raž
    -0.07
    POSITIVE LOGITS
     being
    0.11
     having
    0.11
     Being
    0.08
    being
    0.07
    Being
    0.07
    iron
    0.07
     Having
    0.07
     být
    0.07
    having
    0.06
     être
    0.06
    Activations Density 0.018%

    No Known Activations