© 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. 29773
    Prev
    Next
    INDEX
    Explanations

    instances of the term "dialogue" and its variations

    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
    ll
    -0.09
    cher
    -0.07
    udu
    -0.07
    llll
    -0.07
    ÛĮتÛĮ
    -0.07
    atoes
    -0.07
    /goto
    -0.07
    nici
    -0.07
    Ñģол
    -0.07
    fold
    -0.07
    POSITIVE LOGITS
    ues
    0.09
    istically
    0.08
     between
    0.08
     Between
    0.07
    ative
    0.07
    between
    0.07
    /dialog
    0.07
    ãģĤãģ£ãģŁ
    0.07
    é¢ĺ
    0.06
    omatic
    0.06
    Activations Density 0.007%

    No Known Activations