© 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. 16649
    Prev
    Next
    INDEX
    Explanations

    metrics and statistics related to social media engagement and 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
    iform
    -0.07
    ilerek
    -0.06
     sac
    -0.06
    OLON
    -0.06
    astos
    -0.06
    liable
    -0.06
    Äįin
    -0.06
    covering
    -0.06
    allo
    -0.06
    pone
    -0.06
    POSITIVE LOGITS
     growth
    0.08
     Growth
    0.07
     ÐĿаÑģеление
    0.07
    growth
    0.07
    .fm
    0.07
     overnight
    0.06
    egers
    0.06
     Grow
    0.06
    477
    0.06
     numbers
    0.06
    Activations Density 0.008%

    No Known Activations