© 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. 119050
    Prev
    Next
    INDEX
    Explanations

    phrases related to government and institutional reform

    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
    yonel
    -0.06
    ืà¸Ńà¸Ļ
    -0.06
    çݲ
    -0.06
     fuller
    -0.06
    raya
    -0.06
    /misc
    -0.06
    pite
    -0.06
    ichten
    -0.05
    ë¶
    -0.05
     flock
    -0.05
    POSITIVE LOGITS
     altogether
    0.08
     existing
    0.07
    acha
    0.07
    нÑĸÑģÑĤ
    0.06
    /remove
    0.06
    Ymd
    0.06
     Species
    0.06
     Bowman
    0.06
    existing
    0.06
     existence
    0.06
    Activations Density 0.040%

    No Known Activations