© 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. 76679
    Prev
    Next
    INDEX
    Explanations

    references to professional standards and ethics in journalism

    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
     Stealth
    -0.06
     prec
    -0.05
     Inv
    -0.05
    аÑĢд
    -0.05
     Abram
    -0.05
    ignon
    -0.05
    arta
    -0.05
    aida
    -0.05
     mainland
    -0.05
     cork
    -0.05
    POSITIVE LOGITS
     label
    0.08
    redient
    0.08
    hani
    0.07
     знаком
    0.07
    è¸ı
    0.07
     awarded
    0.07
    .dtd
    0.07
    ĨĴ
    0.07
     seal
    0.07
    olin
    0.07
    Activations Density 0.013%

    No Known Activations