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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 85530
    Prev
    Next
    INDEX
    Explanations

    negative or contrasting statements within texts

    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
    itor
    -0.06
    uzzi
    -0.06
     Rudd
    -0.06
    &S
    -0.06
     tri
    -0.06
    ednou
    -0.06
    Ø´ÙĪ
    -0.06
    ãģĤãĤĬ
    -0.06
    iter
    -0.06
    С
    -0.05
    POSITIVE LOGITS
     neither
    0.14
     nobody
    0.10
     none
    0.10
    Neither
    0.09
     Neither
    0.09
     nowhere
    0.09
     actual
    0.09
    ï¼Į没æľī
    0.09
    ahren
    0.09
    actual
    0.08
    Activations Density 0.042%

    No Known Activations