© 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. 56355
    Prev
    Next
    INDEX
    Explanations

    the presence of auxiliary verbs indicating actions or states

    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
    ique
    -0.07
    idd
    -0.07
    BufferSize
    -0.06
     yesterday
    -0.06
    ised
    -0.06
    idget
    -0.06
    iques
    -0.06
    fg
    -0.06
    ists
    -0.06
    gs
    -0.06
    POSITIVE LOGITS
    kest
    0.08
     magna
    0.07
     cela
    0.07
    RTOS
    0.07
    UMAN
    0.07
    apk
    0.07
     ë£
    0.07
    DBC
    0.07
    ëĿ½
    0.07
    DDL
    0.07
    Activations Density 0.028%

    No Known Activations