© 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. 55861
    Prev
    Next
    INDEX
    Explanations

    themes related to societal issues and consumer behavior

    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
    oleÄį
    -0.08
    @qq
    -0.08
    /*č↵
    -0.06
    vrier
    -0.06
    ynı
    -0.06
     sir
    -0.06
    evice
    -0.06
    vÄĽÅĻ
    -0.06
    ÙĪØŃ
    -0.06
    åĥħ
    -0.06
    POSITIVE LOGITS
     stuff
    0.12
     things
    0.10
     thing
    0.10
     Stuff
    0.10
    stuff
    0.09
    Things
    0.08
    things
    0.08
     Thing
    0.08
    thing
    0.08
     nice
    0.08
    Activations Density 0.101%

    No Known Activations