Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76583
    Prev
    Next
    INDEX
    Explanations

    details related to aquatic environments and their inhabitants

    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
     dri
    -0.07
     Lac
    -0.07
    bo
    -0.06
     infiltr
    -0.06
     padd
    -0.05
    pond
    -0.05
    out
    -0.05
     Bounds
    -0.05
    __
    -0.05
    bounds
    -0.05
    POSITIVE LOGITS
     deep
    0.08
    æ·±
    0.08
    åºķ
    0.08
    ìm
    0.08
     bottom
    0.08
     Scotia
    0.08
     bottoms
    0.08
    byss
    0.07
    ÎŁÎ
    0.07
    alama
    0.07
    Activations Density 0.029%

    No Known Activations