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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89972
    Prev
    Next
    INDEX
    Explanations

    updates or changes in information regarding specific events or reports

    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
    rossover
    -0.07
    tos
    -0.05
     polym
    -0.05
    és
    -0.05
    olib
    -0.05
     bell
    -0.05
    tas
    -0.05
    iper
    -0.05
     pol
    -0.05
    iy
    -0.05
    POSITIVE LOGITS
     original
    0.11
    original
    0.10
     ORIGINAL
    0.10
     earlier
    0.10
     оÑĢиг
    0.09
    .original
    0.09
    ORIGINAL
    0.09
     originals
    0.09
     Earlier
    0.09
     orig
    0.09
    Activations Density 0.004%

    No Known Activations