© 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-32K
    11. 24866
    Prev
    Next
    INDEX
    Explanations

    terms related to medical malpractice and negligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (ls
    -0.16
    inspace
    -0.16
    sport
    -0.15
     offsetof
    -0.15
    rink
    -0.15
    /sites
    -0.15
    .def
    -0.14
    ame
    -0.14
    ERA
    -0.14
     обла
    -0.14
    POSITIVE LOGITS
    ÙĪØ«
    0.19
     treatment
    0.17
     treat
    0.16
     neglig
    0.15
     mortal
    0.15
     reused
    0.15
     leading
    0.15
     treating
    0.15
    WithError
    0.15
     treatments
    0.14
    Activations Density 0.021%

    No Known Activations