© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27576
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and community benefit initiatives

    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
    avern
    -0.06
    pag
    -0.06
    aven
    -0.06
     cors
    -0.06
     Situation
    -0.06
     Raven
    -0.06
     Supply
    -0.06
    inic
    -0.06
    oky
    -0.06
    ny
    -0.06
    POSITIVE LOGITS
     ultimately
    0.11
     Ultimately
    0.09
    Ultimately
    0.08
     thereby
    0.07
     overall
    0.07
     hol
    0.07
     qed
    0.07
     resulting
    0.07
    semb
    0.07
    .Atomic
    0.07
    Activations Density 0.050%

    No Known Activations