© 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. 17-LLAMASCOPE-RES-131K
    11. 16689
    Prev
    Next
    INDEX
    Explanations

    numerical data related to demographics and statistics

    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
    LOBAL
    -0.08
     currently
    -0.07
    缮åīį
    -0.07
    éĻµ
    -0.07
     presently
    -0.07
     Leer
    -0.07
     olduÄŁ
    -0.07
    _Global
    -0.07
    qui
    -0.07
    SizeMode
    -0.07
    POSITIVE LOGITS
    çĶº
    0.07
     Census
    0.06
     total
    0.06
    175
    0.06
     census
    0.06
    170
    0.06
    population
    0.06
     population
    0.06
    417
    0.06
    หว
    0.06
    Activations Density 0.009%

    No Known Activations