© 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. 61958
    Prev
    Next
    INDEX
    Explanations

    issues related to human rights abuses and prison conditions

    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
    éĻħ
    -0.06
    tery
    -0.06
    .allowed
    -0.06
    Adjacent
    -0.06
     moda
    -0.06
    ะ
    -0.06
    ooter
    -0.06
    Probe
    -0.06
    ndl
    -0.06
    ZY
    -0.06
    POSITIVE LOGITS
    vou
    0.08
     returned
    0.07
    return
    0.07
     return
    0.07
    -return
    0.07
     returning
    0.07
     RETURN
    0.06
     dangers
    0.06
    RETURN
    0.06
     Return
    0.06
    Activations Density 0.010%

    No Known Activations