© 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. 735
    Prev
    Next
    INDEX
    Explanations

    references to television broadcasts and viewership metrics

    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
     Tow
    -0.06
    awi
    -0.05
     (
    -0.05
     past
    -0.05
     cos
    -0.05
     independent
    -0.05
    formed
    -0.05
     range
    -0.05
     transfers
    -0.05
     Phot
    -0.05
    POSITIVE LOGITS
    rees
    0.08
    .↵↵↵↵↵↵↵↵↵↵
    0.08
    apon
    0.08
    aset
    0.08
    _marshall
    0.07
    çĦ¦
    0.07
    osu
    0.07
    .↵↵↵↵↵↵↵↵
    0.07
    Presence
    0.07
    راÙĤ
    0.07
    Activations Density 0.017%

    No Known Activations