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. 126541
    Prev
    Next
    INDEX
    Explanations

    expressions of physical intimacy and closeness between characters

    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
    idis
    -0.07
     {{{
    -0.07
    utorials
    -0.07
    æŃ»
    -0.06
    ongyang
    -0.06
    sterol
    -0.06
     lug
    -0.06
    един
    -0.06
     baiser
    -0.06
    -earth
    -0.06
    POSITIVE LOGITS
    æ·
    0.08
    -span
    0.07
    icha
    0.07
     güvenilir
    0.06
    ocha
    0.06
     bottoms
    0.06
    ιÏĩ
    0.06
    Xem
    0.06
     повин
    0.06
    lesen
    0.06
    Activations Density 0.001%

    No Known Activations