© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15761
    Prev
    Next
    INDEX
    Explanations

    phrases related to language, specifically synonyms and euphemisms

    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
    ntity
    -0.07
    obot
    -0.07
    alez
    -0.06
     Mitch
    -0.06
    ëŁ
    -0.06
    ihn
    -0.06
    ALS
    -0.06
    toy
    -0.06
    Wat
    -0.06
    маз
    -0.06
    POSITIVE LOGITS
     saying
    0.09
     means
    0.08
    phrase
    0.07
     basically
    0.07
    esktop
    0.07
     term
    0.07
     Hipp
    0.07
     decir
    0.07
     say
    0.06
     Basically
    0.06
    Activations Density 0.011%

    No Known Activations