© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 22-LLAMASCOPE-RES-131K
    11. 3724
    Prev
    Next
    INDEX
    Explanations

    references to future possibilities and expectations

    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
    æº
    -0.06
     Studios
    -0.06
    subcategory
    -0.06
    á»ħ
    -0.06
    vice
    -0.06
    hil
    -0.06
    à¤Ĥद
    -0.06
    çĭIJ
    -0.06
     Baghd
    -0.06
    ching
    -0.06
    POSITIVE LOGITS
     brings
    0.12
     bring
    0.12
    bring
    0.11
    Bring
    0.10
     bringing
    0.10
     holds
    0.10
     Bring
    0.10
     brought
    0.09
    bringing
    0.09
     hold
    0.08
    Activations Density 0.005%

    No Known Activations