© 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. 1091
    Prev
    Next
    INDEX
    Explanations

    phrases that express universality or totality

    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
    bie
    -0.06
    ong
    -0.06
     Py
    -0.06
     NO
    -0.06
    unes
    -0.05
    imer
    -0.05
     no
    -0.05
     progression
    -0.05
    py
    -0.05
    stoff
    -0.05
    POSITIVE LOGITS
    amon
    0.08
    IRON
    0.07
    ãĤ¤ãĤ¹
    0.07
    uÅŁ
    0.07
    ERSHEY
    0.07
    coil
    0.07
    ATEST
    0.07
    åįĵ
    0.07
    ktop
    0.07
    rani
    0.07
    Activations Density 0.020%

    No Known Activations