© 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. 15-LLAMASCOPE-RES-131K
    11. 27162
    Prev
    Next
    INDEX
    Explanations

    HTML metadata tags and their attributes

    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
    manuel
    -0.07
    çu
    -0.07
    ulumi
    -0.06
    imde
    -0.06
    çuk
    -0.06
    agua
    -0.06
    hte
    -0.06
    çıŃ
    -0.06
    iyon
    -0.06
    ilim
    -0.06
    POSITIVE LOGITS
    angkan
    0.07
    /-
    0.06
    cle
    0.06
    ÑĩеÑĤ
    0.06
     overlay
    0.06
    ê·¼
    0.06
     NEC
    0.06
    DR
    0.06
     Sa
    0.06
    unner
    0.06
    Activations Density 0.000%

    No Known Activations