INDEX

Explanations

keywords and boolean conditions related to programming or logic statements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

/^(

-0.15

åĴ¨

-0.15

eries

-0.15

ÑģÑĤÐ¸Ñĩ

-0.15

ooke

-0.15

unker

-0.14

WithOptions

-0.14

ÙĬØ±Ø§

-0.14

_CHIP

-0.14

ITCH

-0.14

POSITIVE LOGITS

ness

0.16

kim

0.15

ought

0.14

asa

0.14

iness

0.14

ikit

0.14

alf

0.14

linky

0.14

angu

0.14

(True

0.13

Activations Density 0.215%

keywords and boolean conditions related to programming or logic statements

No Comments

No Known Activations