© 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 EvalsExportsAPI 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. 88412
    Prev
    Next
    INDEX
    Explanations

    separations between categories or sections

    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
    MethodImpl
    -0.09
    erez
    -0.08
    ndon
    -0.07
    ablish
    -0.07
    StateException
    -0.07
    ÏĩεδÏĮν
    -0.07
    .scalablytyped
    -0.07
    ÑĪе
    -0.07
    ầm
    -0.07
    å«
    -0.07
    POSITIVE LOGITS
    ferred
    0.06
    an
    0.05
    contro
    0.05
    amp
    0.05
     Stuart
    0.05
     Ged
    0.05
     bulk
    0.05
     itself
    0.05
     leading
    0.05
    _PIXEL
    0.05
    Activations Density 0.005%

    No Known Activations