© 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. 74756
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases that indicate specific usage or purpose

    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
    ever
    -0.07
    oret
    -0.07
    ¼
    -0.07
     meisten
    -0.06
    iver
    -0.06
    коÑĤ
    -0.06
     pari
    -0.06
    OA
    -0.06
    BIT
    -0.06
     across
    -0.06
    POSITIVE LOGITS
     specific
    0.07
    specific
    0.07
     exclusively
    0.07
    //{{
    0.07
     Specific
    0.07
     specifically
    0.07
    'gc
    0.07
     this
    0.07
     конкÑĢеÑĤ
    0.07
    this
    0.06
    Activations Density 0.018%

    No Known Activations