© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 971
    Prev
    Next
    INDEX
    Explanations

    language related to systemic inequality and failed programs

    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
     patriarch
    -0.06
     NÄĽm
    -0.06
    aga
    -0.06
    994
    -0.06
    âĢ¦↵
    -0.06
    ulo
    -0.05
    ony
    -0.05
    rahim
    -0.05
    662
    -0.05
    Leaks
    -0.05
    POSITIVE LOGITS
     tomorrow
    0.10
     future
    0.08
    geist
    0.08
    AMENT
    0.08
    Âłtom
    0.08
    Tomorrow
    0.08
    future
    0.08
     jadx
    0.07
    continue
    0.07
    continued
    0.07
    Activations Density 0.032%

    No Known Activations