INDEX

Explanations

terms related to user interface elements in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ivec

-0.15

undan

-0.15

nect

-0.15

ojis

-0.15

Ð¾Ð¶

-0.14

fir

-0.14

ampire

-0.13

onym

-0.13

nard

-0.13

Î¯Î´Î±

-0.13

POSITIVE LOGITS

_CRC

0.16

.newBuilder

0.15

bons

0.14

olson

0.14

 Kore

0.14

eÅŁit

0.14

_UD

0.14

yor

0.14

 Rotary

0.13

pau

0.13

Activations Density 0.017%

terms related to user interface elements in programming

No Comments

No Known Activations