© 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. 83276
    Prev
    Next
    INDEX
    Explanations

    concepts related to social commentary on dystopia and utopia

    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
     Tango
    -0.07
     LGBT
    -0.07
    995
    -0.06
    æĨ
    -0.06
    CD
    -0.06
     transient
    -0.06
    975
    -0.06
     miser
    -0.06
    993
    -0.06
     Chemistry
    -0.05
    POSITIVE LOGITS
     McL
    0.09
    hlen
    0.08
    aginator
    0.08
    EDIA
    0.07
    že
    0.07
    MediaType
    0.07
    edia
    0.07
    -media
    0.07
    /media
    0.07
    utenberg
    0.07
    Activations Density 0.001%

    No Known Activations