© 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. 40086
    Prev
    Next
    INDEX
    Explanations

    formal communication and official statements

    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
    ch
    -0.06
    240
    -0.06
     ("
    -0.06
    ein
    -0.05
    238
    -0.05
    open
    -0.05
    chat
    -0.05
     tri
    -0.05
    130
    -0.05
     aggress
    -0.05
    POSITIVE LOGITS
    ivan
    0.09
    ktop
    0.08
    GBK
    0.08
    wdx
    0.07
    _accessible
    0.07
    ebek
    0.07
    ModelProperty
    0.07
    laden
    0.07
    ovit
    0.07
    udiant
    0.07
    Activations Density 0.019%

    No Known Activations