© 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. 3837
    Prev
    Next
    INDEX
    Explanations

    scheduled broadcast details and program timings

    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
    amage
    -0.06
    ilo
    -0.06
    èĪĪ
    -0.06
    inho
    -0.06
     staged
    -0.06
    .ng
    -0.06
     Raider
    -0.06
    quit
    -0.06
     personnel
    -0.05
     Jub
    -0.05
    POSITIVE LOGITS
     episode
    0.09
     tune
    0.08
     episodes
    0.08
     Episode
    0.08
     repeat
    0.08
     Episodes
    0.08
    'gc
    0.08
     catch
    0.08
    episode
    0.08
    Catch
    0.08
    Activations Density 0.024%

    No Known Activations