© 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. 129134
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and regulatory requirements concerning data breaches and death registration

    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
    hammer
    -0.06
     sal
    -0.06
     nod
    -0.06
    arp
    -0.06
    _priv
    -0.06
     pest
    -0.06
    stand
    -0.06
    viso
    -0.06
     pir
    -0.06
     lever
    -0.06
    POSITIVE LOGITS
    imas
    0.08
     reporting
    0.07
    )NULL
    0.07
    arih
    0.07
     quarterly
    0.07
    Dashboard
    0.07
     ÑĸнÑĦоÑĢмаÑĨÑĸÑĹ
    0.07
     Dashboard
    0.07
    زÙĬØ©
    0.07
    å»
    0.06
    Activations Density 0.008%

    No Known Activations