© 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. 16331
    Prev
    Next
    INDEX
    Explanations

    concepts related to business development and social media strategies

    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
    COND
    -0.08
    üml
    -0.07
    iyim
    -0.07
    oloj
    -0.07
    ilim
    -0.07
    çĻºè¡¨
    -0.07
    esel
    -0.07
    GuidId
    -0.07
     Walsh
    -0.07
    antha
    -0.07
    POSITIVE LOGITS
     fake
    0.07
    100
    0.07
     Fake
    0.07
    hood
    0.06
     counts
    0.06
     count
    0.06
     Bot
    0.06
     bulk
    0.06
     boost
    0.06
     Farm
    0.06
    Activations Density 0.002%

    No Known Activations