© 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. 128874
    Prev
    Next
    INDEX
    Explanations

    occurrences of phrases that indicate agreements or conditions

    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
    ule
    -0.07
    ú
    -0.06
    op
    -0.06
    ir
    -0.06
    cul
    -0.06
    ullan
    -0.06
    _PRIORITY
    -0.06
    YLE
    -0.05
    sect
    -0.05
    alam
    -0.05
    POSITIVE LOGITS
     any
    0.12
     anything
    0.10
    ä»»ä½ķ
    0.10
    à¹ĥà¸Ķ
    0.09
     everything
    0.09
     all
    0.08
     qualquer
    0.08
    ãģĻãģ¹ãģ¦
    0.08
    any
    0.08
    .any
    0.08
    Activations Density 0.004%

    No Known Activations