© 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. 104748
    Prev
    Next
    INDEX
    Explanations

    actions related to falling or overturning objects

    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
    é¤Ĭ
    -0.08
    åħ»
    -0.07
    avou
    -0.07
    adele
    -0.07
    asma
    -0.07
    arias
    -0.07
    upertino
    -0.07
    jis
    -0.07
    rix
    -0.07
    /comments
    -0.07
    POSITIVE LOGITS
     leaning
    0.09
     leaned
    0.08
     lean
    0.07
     Lean
    0.07
     blocking
    0.07
    lean
    0.07
    転
    0.07
     leans
    0.07
    Lean
    0.07
     tilted
    0.07
    Activations Density 0.020%

    No Known Activations