© 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. 87807
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conflict or tension

    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
    (åľŁ
    -0.09
    (æľ¨
    -0.09
    ãĥĶãĥ¼
    -0.08
    (éĩij
    -0.08
    eç
    -0.07
    eldon
    -0.07
    omik
    -0.07
     ÑħозÑıй
    -0.07
    luet
    -0.07
    ernaut
    -0.07
    POSITIVE LOGITS
     others
    0.07
     prest
    0.06
     actual
    0.06
     Others
    0.06
     actually
    0.06
    hest
    0.06
    az
    0.06
    лем
    0.06
    actually
    0.05
    actual
    0.05
    Activations Density 0.030%

    No Known Activations