© 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. 107037
    Prev
    Next
    INDEX
    Explanations

    terms related to victims and victimization

    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
    oes
    -0.07
    azor
    -0.07
    ØŃÙĬ
    -0.07
    eri
    -0.07
    aris
    -0.07
    erie
    -0.07
    thing
    -0.07
    enta
    -0.07
    inq
    -0.07
    ez
    -0.07
    POSITIVE LOGITS
    hood
    0.11
    andalone
    0.07
    ized
    0.07
     hood
    0.07
    /respond
    0.07
    979
    0.07
    ively
    0.07
     Eis
    0.07
    elist
    0.07
    iation
    0.06
    Activations Density 0.010%

    No Known Activations