© 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. 9-LLAMASCOPE-RES-131K
    11. 95084
    Prev
    Next
    INDEX
    Explanations

    statements and discussions related to individual deaths and the emotional impact on families

    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
    aldo
    -0.07
    lant
    -0.06
    Immutable
    -0.06
    íĬ¼
    -0.06
    IFS
    -0.06
    eger
    -0.06
     cuanto
    -0.06
    uria
    -0.06
    оÑī
    -0.06
    LAB
    -0.06
    POSITIVE LOGITS
    ied
    0.07
    emax
    0.07
    ĶåĽŀ
    0.06
    roman
    0.06
    _REPLACE
    0.06
     à¤ļलत
    0.06
    ongan
    0.06
    IVERS
    0.06
    ueva
    0.06
    cir
    0.06
    Activations Density 0.205%

    No Known Activations