© 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. 125677
    Prev
    Next
    INDEX
    Explanations

    actions and concepts related to commitment and participation

    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
    -0.07
     gra
    -0.06
    yan
    -0.06
    oru
    -0.06
    acker
    -0.06
    ipse
    -0.06
     OnTriggerEnter
    -0.06
    .refs
    -0.06
    oggles
    -0.06
     Krish
    -0.05
    POSITIVE LOGITS
    ãģĵãģĨ
    0.09
     otherwise
    0.08
     elsewhere
    0.08
    Brains
    0.07
     others
    0.07
     Äijó
    0.07
    گاب
    0.07
     accordingly
    0.07
     theirs
    0.07
     them
    0.07
    Activations Density 0.062%

    No Known Activations