© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70926
    Prev
    Next
    INDEX
    Explanations

    phrases centered around the verb "get."

    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
    ercul
    -0.08
    ught
    -0.07
    ials
    -0.07
    .signature
    -0.07
    iliz
    -0.07
    ÃŃnh
    -0.07
     yans
    -0.07
    idel
    -0.07
    ÑĢава
    -0.07
    aliases
    -0.07
    POSITIVE LOGITS
     afforded
    0.07
    isa
    0.06
    ISA
    0.06
    et
    0.06
    ÃŃo
    0.06
    zen
    0.06
     toler
    0.06
     tun
    0.06
     asked
    0.06
    eman
    0.05
    Activations Density 0.024%

    No Known Activations