Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126648
    Prev
    Next
    INDEX
    Explanations

    instances of the word "para" and its variations, indicating a focus on purpose or intention

    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
    reich
    -0.07
    ombo
    -0.06
    do
    -0.06
    lose
    -0.06
    haft
    -0.06
    rossover
    -0.06
    .adv
    -0.06
    cribe
    -0.06
     ÅĻÃŃj
    -0.06
     Dou
    -0.06
    POSITIVE LOGITS
    sÃŃ
    0.09
    tant
    0.09
    bidden
    0.08
    anuts
    0.08
    ãģªãģĦ
    0.08
    ady
    0.08
     sake
    0.07
    s
    0.07
    ître
    0.07
    Ùĩ
    0.07
    Activations Density 0.014%

    No Known Activations