© 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. 4209
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to harm, violence, and injuries

    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
    /new
    -0.07
    asso
    -0.07
    TL
    -0.07
    ego
    -0.06
    PR
    -0.06
    á½°
    -0.06
    aron
    -0.06
    ickey
    -0.06
    eg
    -0.06
    agn
    -0.06
    POSITIVE LOGITS
     somebody
    0.09
     someone
    0.09
     others
    0.08
     anybody
    0.08
    ãĥ¼ãĥ«
    0.07
     anyone
    0.07
     people
    0.07
    others
    0.07
     oppon
    0.07
    someone
    0.07
    Activations Density 0.038%

    No Known Activations