© 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. 4429
    Prev
    Next
    INDEX
    Explanations

    references to journalism or reporters

    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
    orda
    -0.08
    icrous
    -0.07
    gın
    -0.07
    év
    -0.07
    vette
    -0.07
    olon
    -0.07
    vae
    -0.06
    ordo
    -0.06
     now
    -0.06
    ouns
    -0.06
    POSITIVE LOGITS
    RAINT
    0.07
     employer
    0.06
    æ±Ĥ
    0.06
    lain
    0.06
     cig
    0.06
     -*-č↵
    0.06
     employment
    0.06
    Reporting
    0.06
     Employ
    0.06
    ullo
    0.06
    Activations Density 0.000%

    No Known Activations