© 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. 118155
    Prev
    Next
    INDEX
    Explanations

    references to self-harm and individual struggles

    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
    ile
    -0.07
    tot
    -0.06
    205
    -0.06
    arness
    -0.06
    oto
    -0.06
    ensen
    -0.06
     ‘
    -0.05
     elimination
    -0.05
    iland
    -0.05
     stuff
    -0.05
    POSITIVE LOGITS
     themselves
    0.12
     herself
    0.10
    åıĬåħ¶
    0.09
     itself
    0.09
    ãģĿãģĹãģ¦
    0.09
    以åıĬ
    0.09
    /epl
    0.08
     AND
    0.08
    taboola
    0.08
     himself
    0.08
    Activations Density 0.024%

    No Known Activations