© 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. 118717
    Prev
    Next
    INDEX
    Explanations

    references to conflicts or battles involving enemies and defenses

    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
    .LookAndFeel
    -0.08
    ediator
    -0.08
    iland
    -0.07
    avis
    -0.07
    ertime
    -0.07
    å¾Ħ
    -0.07
    ienes
    -0.07
    erras
    -0.07
    Ú¯ÛĮر
    -0.07
    _stuff
    -0.07
    POSITIVE LOGITS
     your
    0.08
    apel
    0.06
    BILE
    0.05
    주ìĿĺ
    0.05
    your
    0.05
     YOUR
    0.05
     YOU
    0.05
     Ùħؤ
    0.05
    unt
    0.05
    änder
    0.05
    Activations Density 0.018%

    No Known Activations