INDEX

Explanations

lines of code or programming-specific syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

inya

-0.17

okit

-0.16

byn

-0.14

ëĿ¼ëıĦ

-0.14

 hatch

-0.14

cab

-0.14

	StringBuffer

-0.14

bern

-0.14

.Glide

-0.14

dorf

-0.14

POSITIVE LOGITS

assert

0.43

 assert

0.43

.Assert

0.40

 assertion

0.38

_assert

0.37

 Assert

0.35

Assert

0.35

 assertions

0.32

	assert

0.32

 asserted

0.31

Activations Density 0.323%

lines of code or programming-specific syntax

No Comments

No Known Activations