© 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. 105389
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and related phrases emphasizing placement or involvement within a context

    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
    arker
    -0.07
    isp
    -0.06
    aci
    -0.06
    ardo
    -0.06
     Ziel
    -0.06
     Verm
    -0.06
     Kara
    -0.06
     mut
    -0.06
     Kostenlose
    -0.06
    isor
    -0.06
    POSITIVE LOGITS
    .struts
    0.08
    avar
    0.07
    adel
    0.07
    iddy
    0.07
    ictor
    0.07
    \Blueprint
    0.07
    icht
    0.06
    397
    0.06
    _ck
    0.06
    hevik
    0.06
    Activations Density 0.017%

    No Known Activations