© 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. 107135
    Prev
    Next
    INDEX
    Explanations

    terms related to degrees and classifications of murder

    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
    iek
    -0.07
    nett
    -0.07
    rod
    -0.07
    pong
    -0.06
    //--------------------------------------------------------------------------------
    -0.06
    æݪ
    -0.06
    rab
    -0.06
    lexical
    -0.06
    otel
    -0.06
    ково
    -0.06
    POSITIVE LOGITS
    /th
    0.09
    ansa
    0.08
    ped
    0.07
    uten
    0.07
    /type
    0.07
    -level
    0.07
     Beitrag
    0.06
    aug
    0.06
     tier
    0.06
    -tier
    0.06
    Activations Density 0.005%

    No Known Activations