© 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. 82669
    Prev
    Next
    INDEX
    Explanations

    specific named events or occurrences

    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
    ÙĪرد
    -0.08
    ÑĢиÑĩ
    -0.07
    ÅĻet
    -0.07
    коÑĢ
    -0.07
    .cx
    -0.07
    é±¼
    -0.07
     anlayÄ±ÅŁ
    -0.07
    leton
    -0.07
    idal
    -0.07
    neau
    -0.07
    POSITIVE LOGITS
    (PR
    0.07
     press
    0.06
     Vice
    0.06
    731
    0.06
     said
    0.06
     hol
    0.05
     Cater
    0.05
     ###↵
    0.05
    .ly
    0.05
    swire
    0.05
    Activations Density 0.025%

    No Known Activations