© 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. 3927
    Prev
    Next
    INDEX
    Explanations

    health-related criteria and medical conditions

    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
    vier
    -0.09
    ingham
    -0.09
    avar
    -0.09
    zin
    -0.08
    ieder
    -0.08
     trang
    -0.08
     skoro
    -0.08
    CCR
    -0.07
    _specs
    -0.07
     (~(
    -0.07
    POSITIVE LOGITS
     recent
    0.07
     recently
    0.07
     anything
    0.06
     active
    0.06
     or
    0.06
     foreign
    0.06
     currently
    0.06
     any
    0.06
     contr
    0.06
     history
    0.06
    Activations Density 0.009%

    No Known Activations