© 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. 125881
    Prev
    Next
    INDEX
    Explanations

    themes of extraordinary abilities and adventurous heroism

    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
    .ravel
    -0.07
    .managed
    -0.07
    ãģĵãĤĵãģ«
    -0.07
    vertise
    -0.07
    akit
    -0.07
    ÑģÑĤÑĥп
    -0.07
    åµ
    -0.07
    鬼
    -0.07
     خرد
    -0.07
    ascal
    -0.07
    POSITIVE LOGITS
     powers
    0.15
     Powers
    0.13
     abilities
    0.11
    powers
    0.11
     super
    0.10
     capabilities
    0.10
     power
    0.09
     capability
    0.09
     Super
    0.08
     powered
    0.08
    Activations Density 0.085%

    No Known Activations