© 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. 15-LLAMASCOPE-RES-131K
    11. 104112
    Prev
    Next
    INDEX
    Explanations

    temporal indicators and their relationships

    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
    ожеÑĤ
    -0.06
     Offensive
    -0.06
    ideos
    -0.06
    æĭ©
    -0.06
     springfox
    -0.06
    obb
    -0.06
    oland
    -0.06
    oÅĪ
    -0.06
     authDomain
    -0.06
    vey
    -0.06
    POSITIVE LOGITS
     Greg
    0.08
    greg
    0.07
     Julian
    0.07
    ena
    0.07
    ilian
    0.07
    Greg
    0.07
    uled
    0.07
    eras
    0.06
    aro
    0.06
    odos
    0.06
    Activations Density 0.001%

    No Known Activations