© 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. 56301
    Prev
    Next
    INDEX
    Explanations

    information related to healthcare systems and technology

    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
    SURE
    -0.07
    679
    -0.07
    EFA
    -0.07
    lech
    -0.07
    å¥Ī
    -0.07
    기ìĪł
    -0.07
    .removeListener
    -0.06
    .Unity
    -0.06
    mour
    -0.06
    ä¿Ĺ
    -0.06
    POSITIVE LOGITS
    oad
    0.07
    onz
    0.06
    UDO
    0.06
    oil
    0.06
    usic
    0.06
    eniable
    0.06
     Cannon
    0.06
    ounty
    0.06
    ebi
    0.06
    count
    0.05
    Activations Density 0.060%

    No Known Activations