© 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. 9-LLAMASCOPE-RES-131K
    11. 95850
    Prev
    Next
    INDEX
    Explanations

    references to observation and perspective in a narrative 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
    ãĥ¼ãĥ
    -0.08
    ellan
    -0.08
    λÏī
    -0.07
    MOTE
    -0.07
     localVar
    -0.07
    ÃŃky
    -0.07
    Äĥn
    -0.07
    OffsetTable
    -0.07
    ERRU
    -0.07
    iset
    -0.07
    POSITIVE LOGITS
    ream
    0.07
    aign
    0.06
    ast
    0.06
    _
    0.06
    ŀ
    0.06
    alert
    0.06
    rd
    0.06
    yas
    0.05
    Us
    0.05
     Lore
    0.05
    Activations Density 0.003%

    No Known Activations