© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 63182
    Prev
    Next
    INDEX
    Explanations

    phrases related to cycles and their impacts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     McGu
    -0.08
    ekler
    -0.07
    landers
    -0.07
    _CID
    -0.06
    uada
    -0.06
    onaut
    -0.06
    hey
    -0.06
    /fw
    -0.06
    etch
    -0.06
    ãĥĩãĥ«
    -0.06
    POSITIVE LOGITS
     between
    0.07
     of
    0.07
    orro
    0.06
    /link
    0.06
    ZA
    0.06
    -like
    0.06
    prus
    0.06
     междÑĥ
    0.06
    å¼ı
    0.06
    èĪ¬
    0.06
    Activations Density 0.025%

    No Known Activations