© 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. 93784
    Prev
    Next
    INDEX
    Explanations

    phrases that express relationships or affiliations, particularly focusing on the word "of"

    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
     slope
    -0.06
    ina
    -0.06
    535
    -0.06
     sheer
    -0.06
     with
    -0.06
    tree
    -0.06
     at
    -0.06
     by
    -0.06
    ilda
    -0.06
     Ñģвоими
    -0.05
    POSITIVE LOGITS
    chin
    0.08
    riter
    0.07
    cher
    0.07
     ÙħخصÙĪص
    0.07
    avl
    0.07
    atürk
    0.07
    Äįan
    0.07
    sonian
    0.07
    .cbo
    0.07
    Feat
    0.07
    Activations Density 0.027%

    No Known Activations