© 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. 40410
    Prev
    Next
    INDEX
    Explanations

    references to violence and harmful ideologies, particularly relating to genocide and oppression

    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
    less
    -0.06
    ãĥĬ
    -0.06
    746
    -0.05
    yth
    -0.05
    628
    -0.05
     sparing
    -0.05
    a
    -0.05
    shop
    -0.05
    -less
    -0.05
    aint
    -0.05
    POSITIVE LOGITS
    avou
    0.09
    tuk
    0.09
    apesh
    0.08
    hoot
    0.08
    ersive
    0.08
    eryl
    0.08
    знаÑĩа
    0.08
    -pills
    0.07
    à¸Ļà¸Ħ
    0.07
    bard
    0.07
    Activations Density 0.072%

    No Known Activations