© 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. 9-LLAMASCOPE-RES-131K
    11. 95501
    Prev
    Next
    INDEX
    Explanations

    quantifiers expressing minimum thresholds or amounts

    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
    mpar
    -0.07
    elease
    -0.07
    irie
    -0.07
     Ïį
    -0.07
    activex
    -0.07
    lice
    -0.07
    .Disclaimer
    -0.07
    uale
    -0.07
     tô
    -0.07
     Rosenstein
    -0.07
    POSITIVE LOGITS
    ingo
    0.06
    940
    0.06
     no
    0.06
    427
    0.06
    avad
    0.05
     yet
    0.05
     Tanner
    0.05
     Al
    0.05
    fault
    0.05
    емо
    0.05
    Activations Density 0.004%

    No Known Activations