© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80904
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of documents or records

    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
    ↵
    -0.07
    ly
    -0.07
     separate
    -0.07
    代
    -0.06
    iy
    -0.06
     Patri
    -0.06
    z
    -0.06
    ise
    -0.06
     seperate
    -0.06
    de
    -0.06
    POSITIVE LOGITS
    /cop
    0.11
    ibbon
    0.09
    .deepcopy
    0.09
    arges
    0.08
    .SpringBootTest
    0.08
    actus
    0.08
    eniable
    0.08
    agua
    0.07
    olicies
    0.07
    usher
    0.07
    Activations Density 0.007%

    No Known Activations