© 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. 106860
    Prev
    Next
    INDEX
    Explanations

    terms related to prevention and intervention strategies for at-risk youth

    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
    ino
    -0.06
    inosaur
    -0.06
    ohn
    -0.06
    INO
    -0.06
    rne
    -0.06
     con
    -0.06
     press
    -0.05
    secutive
    -0.05
     Rosenstein
    -0.05
     Fle
    -0.05
    POSITIVE LOGITS
     preempt
    0.14
     pre
    0.12
     early
    0.11
    -pre
    0.11
    é¢Ħ
    0.10
    /pre
    0.10
     é¢Ħ
    0.10
     prevention
    0.10
    	pre
    0.10
    _pre
    0.10
    Activations Density 0.051%

    No Known Activations