© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126353
    Prev
    Next
    INDEX
    Explanations

    instances of conditional phrases and clauses

    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
    ume
    -0.08
    جاد
    -0.07
    ɵ
    -0.07
     irgend
    -0.07
    apk
    -0.07
    xdb
    -0.07
    onta
    -0.07
    erset
    -0.07
    ernaut
    -0.07
    ÅĤÄħ
    -0.07
    POSITIVE LOGITS
     already
    0.11
     clearly
    0.09
     Already
    0.08
    Already
    0.07
    already
    0.07
     barely
    0.07
    _already
    0.07
     consider
    0.07
    è¿Ļä¹Ī
    0.06
    å¦ĤæŃ¤
    0.06
    Activations Density 0.054%

    No Known Activations