© 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 EvalsExportsinterp-engineNEWAPI 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. 117948
    Prev
    Next
    INDEX
    Explanations

    constantly repeated phrases indicating a sense of inevitability or persistence

    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
    ntax
    -0.08
    zan
    -0.07
    .scalablytyped
    -0.07
    &view
    -0.07
    ä»°
    -0.07
    (?:
    -0.07
     AÅŁ
    -0.07
    vil
    -0.07
    okino
    -0.07
    plen
    -0.06
    POSITIVE LOGITS
     anymore
    0.10
     necessarily
    0.08
    ori
    0.07
    à¹Ħหà¸Ļ
    0.07
    0.07
     any
    0.06
     rocket
    0.06
    ae
    0.06
     likely
    0.06
     Conv
    0.06
    Activations Density 0.013%

    No Known Activations