© 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. 75643
    Prev
    Next
    INDEX
    Explanations

    references to arrests and legal 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
    ersiz
    -0.07
    osate
    -0.07
    ccione
    -0.07
    .updateDynamic
    -0.06
    bern
    -0.06
    主人
    -0.06
    áºł
    -0.06
    crate
    -0.06
    Cover
    -0.06
     æ¬
    -0.06
    POSITIVE LOGITS
    uffer
    0.09
    0.06
     зад
    0.06
    rending
    0.06
    次
    0.06
     booking
    0.06
    _RUNTIME
    0.06
    otas
    0.06
    emi
    0.06
    usz
    0.06
    Activations Density 0.000%

    No Known Activations