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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 105546
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific integrity and trustworthiness

    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
     teil
    -0.07
    身ä¸Ĭ
    -0.06
     totally
    -0.06
     Planet
    -0.06
    eee
    -0.06
    olf
    -0.06
    acha
    -0.06
    ulti
    -0.05
    inky
    -0.05
    egrate
    -0.05
    POSITIVE LOGITS
    nesc
    0.07
    uba
    0.07
    ingles
    0.06
    UNET
    0.06
    elyn
    0.06
    ÌĢ
    0.06
    Wunused
    0.06
    ìļ´
    0.06
    IGO
    0.06
     YYS
    0.06
    Activations Density 0.000%

    No Known Activations