© 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. 28724
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurements and sequencing

    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
     btw
    -0.06
    егоÑĢ
    -0.06
     versus
    -0.06
     thereby
    -0.06
    orthy
    -0.06
     consort
    -0.05
     quoi
    -0.05
     Ãĥ
    -0.05
     Ramp
    -0.05
     далÑĮ
    -0.05
    POSITIVE LOGITS
     naopak
    0.12
     Conversely
    0.08
    æ¸Ī
    0.08
    åīĩ
    0.08
     *)((
    0.08
    ãģĵãģ¡ãĤī
    0.07
    ibili
    0.07
     mnohem
    0.07
    deaux
    0.07
     more
    0.07
    Activations Density 0.081%

    No Known Activations