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

    Neuronpedia

    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. 58039
    Prev
    Next
    INDEX
    Explanations

    repeated phrases emphasizing the concept of "more" in various contexts

    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
     than
    -0.08
    _than
    -0.06
     Sang
    -0.06
    senal
    -0.06
    _invoke
    -0.06
     Durch
    -0.06
    auses
    -0.06
    apor
    -0.06
     THAN
    -0.06
    267
    -0.06
    POSITIVE LOGITS
    DCF
    0.08
     we
    0.08
     they
    0.08
    ìĦĿ
    0.07
    è¾°
    0.07
    egative
    0.07
    ROOM
    0.07
     vite
    0.06
     you
    0.06
    liest
    0.06
    Activations Density 0.004%

    No Known Activations