© 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. 95868
    Prev
    Next
    INDEX
    Explanations

    phrases related to job opportunities and visibility

    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
    bih
    -0.08
    imid
    -0.07
    izzo
    -0.07
    зв
    -0.07
    isoft
    -0.07
     residue
    -0.06
    imo
    -0.06
     Shore
    -0.06
    Configurer
    -0.06
     quả
    -0.06
    POSITIVE LOGITS
    íĤ
    0.06
    957
    0.06
    ½
    0.06
     McLaren
    0.06
     MERCHANTABILITY
    0.06
    ãĥ¼ãĥijãĥ¼
    0.06
    oks
    0.05
    avad
    0.05
    infos
    0.05
    æľĹ
    0.05
    Activations Density 0.070%

    No Known Activations