© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84157
    Prev
    Next
    INDEX
    Explanations

    elements related to physical sensations and 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
    o
    -0.06
    umi
    -0.05
     circle
    -0.05
    434
    -0.05
    qué
    -0.05
    __.
    -0.05
     Dim
    -0.05
     Historic
    -0.05
     cheap
    -0.05
    ott
    -0.05
    POSITIVE LOGITS
     Garc
    0.10
    presso
    0.08
    alace
    0.08
    ebek
    0.08
    czy
    0.08
    (æ°´
    0.07
    urum
    0.07
    ÄĽlÃŃ
    0.07
    apgolly
    0.07
    ecies
    0.07
    Activations Density 0.001%

    No Known Activations