© 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. 106656
    Prev
    Next
    INDEX
    Explanations

    elements related to social interaction and community support

    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
     however
    -0.10
    ìĿ´ê³ł
    -0.10
     totiž
    -0.09
    ãģ§ãģĤãĤĬ
    -0.08
    ;
    -0.08
    )&&(
    -0.08
    however
    -0.08
     és
    -0.08
     and
    -0.08
    And
    -0.07
    POSITIVE LOGITS
     accordingly
    0.15
     consequently
    0.09
    egl
    0.08
     Accordingly
    0.07
     Ø¢ÙĨ
    0.07
    алом
    0.07
    alian
    0.07
     Pearson
    0.07
    )prepare
    0.07
     therap
    0.07
    Activations Density 0.442%

    No Known Activations