© 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. 128756
    Prev
    Next
    INDEX
    Explanations

    references to different sections or chapters of written works

    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
     Trout
    -0.07
    weed
    -0.07
    bane
    -0.07
    ROUT
    -0.07
    opi
    -0.07
    bell
    -0.07
    .mixin
    -0.07
    ednou
    -0.07
    _flutter
    -0.06
     Král
    -0.06
    POSITIVE LOGITS
     devoted
    0.14
     dedicated
    0.13
     dealing
    0.08
     called
    0.08
     titled
    0.07
     about
    0.07
    ded
    0.07
     Dedicated
    0.07
     separate
    0.07
     dedicate
    0.07
    Activations Density 0.028%

    No Known Activations