© 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. 77232
    Prev
    Next
    INDEX
    Explanations

    themes related to moral accountability and the need for repentance

    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
    ainter
    -0.10
    overn
    -0.08
    uess
    -0.08
    ISTA
    -0.07
    odzi
    -0.07
    unsupported
    -0.07
    acock
    -0.07
    UMMY
    -0.07
    ductor
    -0.07
    زار
    -0.07
    POSITIVE LOGITS
    387
    0.07
     confession
    0.06
     sin
    0.06
    -f
    0.06
     leading
    0.06
     part
    0.06
     kle
    0.06
     pen
    0.06
     dispose
    0.06
    mit
    0.06
    Activations Density 0.024%

    No Known Activations