INDEX

Explanations

mentions of the NHL (National Hockey League) in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ama

-0.15

Ð¾Ð»ÑĮÐ½Ð¾

-0.15

eel

-0.15

akter

-0.14

wdx

-0.14

nze

-0.14

vatel

-0.14

eah

-0.14

ledon

-0.14

NgModule

-0.14

POSITIVE LOGITS

 itself

0.16

mie

0.15

ugu

0.14

Å¼y

0.14

rd

0.14

 thá»¥

0.14

 Western

0.14

ro

0.13

CLOCKS

0.13

Activations Density 0.002%

mentions of the NHL (National Hockey League) in various contexts

No Comments

No Known Activations