© 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. 17-LLAMASCOPE-RES-131K
    11. 59856
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and descriptions of actions involving characters

    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
     or
    -0.07
     recent
    -0.06
    coon
    -0.06
     when
    -0.06
     Burst
    -0.06
     (
    -0.06
    wer
    -0.05
    onds
    -0.05
    lag
    -0.05
     grab
    -0.05
    POSITIVE LOGITS
     ê³ĦìĨį
    0.10
    Until
    0.08
    .until
    0.08
    继ç»Ń
    0.08
     until
    0.08
    until
    0.08
     Until
    0.08
    sWith
    0.08
    ãi
    0.08
    .↵↵↵↵↵↵↵↵
    0.07
    Activations Density 0.037%

    No Known Activations