© 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. 17-LLAMASCOPE-RES-131K
    11. 77591
    Prev
    Next
    INDEX
    Explanations

    references to academic competitions and student projects

    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
    ób
    -0.07
    essler
    -0.07
    å®ħ
    -0.07
    ValueCollection
    -0.07
    lesia
    -0.06
    OPS
    -0.06
    illos
    -0.06
    æŁı
    -0.06
     Spieler
    -0.06
     Ple
    -0.06
    POSITIVE LOGITS
     pitch
    0.08
     presentations
    0.08
     pitching
    0.07
     presentation
    0.07
     pitches
    0.07
     award
    0.07
     pitchers
    0.07
     Pitch
    0.07
     winning
    0.07
     competition
    0.07
    Activations Density 0.004%

    No Known Activations