© 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. 22-LLAMASCOPE-RES-131K
    11. 4029
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing or resolving problems

    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
     Specs
    -0.06
     ìŬ룬ë¶Ħ
    -0.06
    üh
    -0.06
     Relevant
    -0.06
    emoc
    -0.06
     ÅŁÃ¶yle
    -0.06
     compromised
    -0.06
     luxe
    -0.06
    ãģĵãĤį
    -0.06
    絶
    -0.06
    POSITIVE LOGITS
    ence
    0.07
    æ¿
    0.07
    zie
    0.06
    gren
    0.06
     recount
    0.06
     continually
    0.06
    .SwingConstants
    0.06
     normally
    0.06
     apparently
    0.06
    (tm
    0.06
    Activations Density 0.002%

    No Known Activations