© 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. 78385
    Prev
    Next
    INDEX
    Explanations

    references to political actions or events

    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
     whilst
    -0.09
    owards
    -0.08
    âĶ¬
    -0.07
     Whilst
    -0.07
    -0.07
     seperate
    -0.07
     entirety
    -0.06
     endeavour
    -0.06
     similar
    -0.06
     continued
    -0.06
    POSITIVE LOGITS
    -plus
    0.10
     sez
    0.08
     pronto
    0.07
    REMOTE
    0.07
     schle
    0.07
    ãģĵãĤĵ
    0.07
     prefab
    0.07
     precisely
    0.07
    dana
    0.06
     ÂŃ
    0.06
    Activations Density 2.070%

    No Known Activations