© 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. 28768
    Prev
    Next
    INDEX
    Explanations

    references to skills application and practical training in academic contexts

    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
     звиÑĩай
    -0.07
    ifikasi
    -0.07
    PLEX
    -0.07
    postalcode
    -0.07
    pty
    -0.07
    addtogroup
    -0.06
    lak
    -0.06
    álido
    -0.06
    gent
    -0.06
    (iOS
    -0.06
    POSITIVE LOGITS
     learned
    0.12
     learnt
    0.11
     lessons
    0.10
     learn
    0.10
     newfound
    0.09
     knowledge
    0.09
     Learned
    0.09
    lessons
    0.09
    learn
    0.09
     Lessons
    0.09
    Activations Density 0.016%

    No Known Activations