© 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. 5-LLAMASCOPE-RES-131K
    11. 126552
    Prev
    Next
    INDEX
    Explanations

    references to video game titles and their associated features

    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
    iche
    -0.07
    ector
    -0.07
    arten
    -0.07
    ipel
    -0.06
    RelativeTo
    -0.06
     gal
    -0.06
     ifndef
    -0.06
    LOTS
    -0.06
    lds
    -0.06
    ahn
    -0.06
    POSITIVE LOGITS
    abbage
    0.07
    physics
    0.07
     physics
    0.06
    _ctxt
    0.06
    åĪ»
    0.06
     fx
    0.06
    ruc
    0.06
    isd
    0.06
    _dicts
    0.06
    lum
    0.06
    Activations Density 0.012%

    No Known Activations