© 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. 95713
    Prev
    Next
    INDEX
    Explanations

    noun phrases referring to specific items or categories related to accessories and clothing

    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
    itin
    -0.06
    itis
    -0.06
    itr
    -0.06
    iti
    -0.05
     matching
    -0.05
     corresponding
    -0.05
    hir
    -0.05
     correspond
    -0.05
     ex
    -0.05
     Umb
    -0.05
    POSITIVE LOGITS
     anytime
    0.09
    ä»»ä½ķ
    0.08
     any
    0.08
     bất
    0.08
     каÑĩеÑģÑĤве
    0.08
     cualquier
    0.08
     qualquer
    0.08
     anywhere
    0.08
    lescope
    0.07
     ########.
    0.07
    Activations Density 0.017%

    No Known Activations