INDEX

Explanations

programming or coding-related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

$MESS

-0.18

 pessim

-0.16

ÎµÎ¯

-0.15

ÑĮÐµ

-0.15

esk

-0.15

Ð¬

-0.15

lon

-0.15

aukee

-0.14

.pretty

-0.14

swire

-0.14

POSITIVE LOGITS

imum

0.16

NIL

0.15

wil

0.14

imal

0.14

icity

0.14

ioned

0.14

ument

0.14

ome

0.14

eways

0.14

omed

0.14

Activations Density 0.001%

programming or coding-related keywords

No Comments

No Known Activations