© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16713
    Prev
    Next
    INDEX
    Explanations

    punctuation, particularly colons and periods, as well as mentions of people and places

    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
    aga
    -0.06
    j
    -0.06
    ache
    -0.06
     anc
    -0.06
     ´
    -0.06
    achel
    -0.05
    tir
    -0.05
    nu
    -0.05
    estival
    -0.05
    613
    -0.05
    POSITIVE LOGITS
     Firstly
    0.08
     Gio
    0.07
     ÐĴики
    0.07
    VEC
    0.07
    PHA
    0.07
    odem
    0.07
     aside
    0.07
     First
    0.07
    pedia
    0.07
    #__
    0.07
    Activations Density 0.036%

    No Known Activations