© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72168
    Prev
    Next
    INDEX
    Explanations

    key terms related to significant and formal concepts in contexts such as performance, penalties, or structural nuances

    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
    arel
    -0.09
    ','');↵
    -0.06
     ìŀĪëĭ¤ê³ł
    -0.06
    ayer
    -0.06
     NavParams
    -0.06
    ARGER
    -0.06
    POSIT
    -0.06
    caret
    -0.06
    353
    -0.06
    िण
    -0.05
    POSITIVE LOGITS
     plus
    0.25
    ï¼Į以åıĬ
    0.20
    以åıĬ
    0.19
    plus
    0.19
     PLUS
    0.18
     oraz
    0.18
     sowie
    0.17
     samt
    0.16
     along
    0.16
     ainsi
    0.15
    Activations Density 0.000%

    No Known Activations