© 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. 15-LLAMASCOPE-RES-131K
    11. 87708
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "with."

    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
    aight
    -0.09
    ourg
    -0.08
    arpa
    -0.08
    ysi
    -0.08
    Ĺ
    -0.08
    odzi
    -0.08
    uluk
    -0.08
    輪
    -0.08
    /Dk
    -0.08
    ureau
    -0.07
    POSITIVE LOGITS
     a
    0.08
    p
    0.07
     an
    0.07
    mi
    0.07
    an
    0.06
    1
    0.06
     non
    0.06
    appropri
    0.06
    a
    0.06
    m
    0.06
    Activations Density 0.029%

    No Known Activations