INDEX

Explanations

code snippets related to software development or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oux

-0.18

han

-0.15

 Programming

-0.15

 gubern

-0.15

uc

-0.14

mitt

-0.14

per

-0.14

ens

-0.14

itor

-0.14

POSITIVE LOGITS

ãĥ³ãĥĦ

0.16

ãĥ«ãĤ¯

0.16

.fits

0.15

iyel

0.15

ãĥ³ãĥĪ

0.15

printStats

0.14

ieme

0.14

ãĥ£

0.14

åįĵ

0.14

ITLE

0.14

Activations Density 0.033%

code snippets related to software development or programming concepts

No Comments

No Known Activations