© 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. 121286
    Prev
    Next
    INDEX
    Explanations

    titles of sections or content in documents

    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
    cum
    -0.08
    IPP
    -0.07
    066
    -0.07
    Ñģим
    -0.07
    ’ta
    -0.07
    cus
    -0.07
    Ư
    -0.07
    uten
    -0.07
     WINAPI
    -0.07
    eso
    -0.07
    POSITIVE LOGITS
    aney
    0.06
     Chow
    0.06
    anim
    0.05
    GenericType
    0.05
    xing
    0.05
     generosity
    0.05
     Lorenzo
    0.05
     Maur
    0.05
    avig
    0.05
    ön
    0.05
    Activations Density 0.000%

    No Known Activations