© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 85018
    Prev
    Next
    INDEX
    Explanations

    terms related to influencer marketing and social media influence

    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
    spiel
    -0.07
    -await
    -0.06
    andan
    -0.06
    ezi
    -0.06
    olly
    -0.06
    anden
    -0.06
    kas
    -0.06
    esch
    -0.06
    antium
    -0.06
    Head
    -0.06
    POSITIVE LOGITS
    rella
    0.07
    ential
    0.07
     Payload
    0.06
    inka
    0.06
     superf
    0.06
    วà¸ĩ
    0.06
    ÙģØ§Øª
    0.06
    èĨľ
    0.06
    Defined
    0.06
    .instagram
    0.06
    Activations Density 0.003%

    No Known Activations