© 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. 124108
    Prev
    Next
    INDEX
    Explanations

    words related to discussing or explaining topics, especially in the context of comparisons or specifications

    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
    .scalablytyped
    -0.08
    BITS
    -0.08
    iddet
    -0.07
    ROTO
    -0.07
    áºŃt
    -0.07
    oret
    -0.07
    SETS
    -0.07
    جÙĩ
    -0.07
     huku
    -0.07
    .Dev
    -0.07
    POSITIVE LOGITS
    this
    0.08
    [this
    0.07
     this
    0.07
    ê·¹
    0.06
    htar
    0.06
    rant
    0.06
     whether
    0.06
     damned
    0.06
    ssue
    0.05
    élé
    0.05
    Activations Density 0.041%

    No Known Activations