© 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. 87300
    Prev
    Next
    INDEX
    Explanations

    terms related to vacuum and suction in various contexts

    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
    iard
    -0.07
    edelta
    -0.07
    onn
    -0.07
    amon
    -0.07
    à¹Ĥà¸ķ
    -0.06
    biz
    -0.06
    á»Ĩ
    -0.06
    ":[{↵
    -0.06
    asic
    -0.06
    ynchron
    -0.06
    POSITIVE LOGITS
    ing
    0.09
    uum
    0.08
    arta
    0.08
     cleaner
    0.08
    eer
    0.07
     cleaners
    0.06
     drawn
    0.06
    ed
    0.06
    dal
    0.06
    áze
    0.06
    Activations Density 0.005%

    No Known Activations