© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 40867
    Prev
    Next
    INDEX
    Explanations

    references to innocence and the concept of innocent individuals

    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
    illisecond
    -0.10
    gings
    -0.08
    ÑĥнкÑĤ
    -0.08
    istrovstvÃŃ
    -0.08
    ÑģоÑĤ
    -0.08
    tle
    -0.08
    sono
    -0.08
    onomy
    -0.08
    arith
    -0.08
    lfw
    -0.07
    POSITIVE LOGITS
     innocent
    0.10
     innocence
    0.09
     innoc
    0.08
     Innoc
    0.08
     bystand
    0.08
    -looking
    0.08
    /simple
    0.07
     inoc
    0.07
     unsus
    0.07
    nes
    0.07
    Activations Density 0.005%

    No Known Activations