© 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. 16626
    Prev
    Next
    INDEX
    Explanations

    references to academic programs and degrees offered by a university

    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
    åı
    -0.07
    etz
    -0.06
    @dynamic
    -0.06
     boot
    -0.06
    ét
    -0.06
    Matchers
    -0.06
    orners
    -0.05
     Universities
    -0.05
    avir
    -0.05
    antt
    -0.05
    POSITIVE LOGITS
     Programs
    0.07
     Barrier
    0.07
    loat
    0.07
    choices
    0.07
    Translator
    0.07
     offerings
    0.06
    translator
    0.06
    ocache
    0.06
    alsex
    0.06
    inez
    0.06
    Activations Density 0.013%

    No Known Activations