© 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. 126399
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to communication protocols

    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
    864
    -0.08
     SPDX
    -0.08
    ceptar
    -0.07
    urat
    -0.07
    ãĤīãģ®
    -0.06
    baugh
    -0.06
    UNC
    -0.06
     States
    -0.06
     Isles
    -0.06
    uard
    -0.06
    POSITIVE LOGITS
    -packed
    0.08
    packed
    0.07
     Hust
    0.07
     packed
    0.07
     Pack
    0.07
     pack
    0.07
    pack
    0.07
     Magic
    0.07
     Reserved
    0.07
     reserved
    0.07
    Activations Density 0.283%

    No Known Activations