© 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. 104875
    Prev
    Next
    INDEX
    Explanations

    words related to extermination or removal, particularly in a violent or extreme context

    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
    usz
    -0.07
    a
    -0.06
    gaard
    -0.06
     adj
    -0.06
    te
    -0.06
    nge
    -0.06
    æĬķ
    -0.06
    ogan
    -0.06
    ughters
    -0.06
    sburg
    -0.06
    POSITIVE LOGITS
    insic
    0.07
    isor
    0.07
    ldre
    0.07
    istor
    0.07
    ience
    0.06
    lrt
    0.06
    trie
    0.06
    ccess
    0.06
    .ManyToMany
    0.06
    GEN
    0.06
    Activations Density 0.000%

    No Known Activations