© 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. 74187
    Prev
    Next
    INDEX
    Explanations

    references to sections and equations within a document

    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
     yesterday
    -0.06
     nearest
    -0.06
     v
    -0.05
    ould
    -0.05
    erd
    -0.05
     rem
    -0.05
     causal
    -0.05
     hot
    -0.05
     davon
    -0.05
     Classified
    -0.05
    POSITIVE LOGITS
     throughout
    0.12
    Throughout
    0.12
     Throughout
    0.12
    'gc
    0.08
    discussion
    0.08
     discussions
    0.08
    ascus
    0.08
    .scalablytyped
    0.08
    anken
    0.08
     boyunca
    0.07
    Activations Density 0.047%

    No Known Activations