© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118100
    Prev
    Next
    INDEX
    Explanations

    themes related to political criticism and commentary, particularly regarding left-wing groups and their actions

    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
    شتÙĩ
    -0.06
    AREN
    -0.06
    izzo
    -0.06
     Craig
    -0.06
    ITO
    -0.06
    988
    -0.06
    Enumerator
    -0.06
    634
    -0.06
    178
    -0.06
     eventually
    -0.06
    POSITIVE LOGITS
     instead
    0.10
    instead
    0.08
    esa
    0.08
     Instead
    0.08
    _exceptions
    0.08
    Instead
    0.07
    ãģ°ãģĭãĤĬ
    0.07
    .eng
    0.07
    оÑī
    0.07
    /lists
    0.07
    Activations Density 0.034%

    No Known Activations