© 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. 103620
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities 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
    amo
    -0.07
    eda
    -0.06
    977
    -0.06
    borg
    -0.06
    zie
    -0.06
    ulace
    -0.06
    ws
    -0.06
    undle
    -0.06
    iverse
    -0.06
    cha
    -0.06
    POSITIVE LOGITS
     single
    0.10
    single
    0.09
    -single
    0.08
    /single
    0.08
    åIJĮæĻĤ
    0.08
     simultaneously
    0.08
    ä¸Ģèµ·
    0.07
     together
    0.07
    åIJĮæŶ
    0.07
    thag
    0.07
    Activations Density 0.035%

    No Known Activations