INDEX

Explanations

references to data structures and arrays 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

bolt

-0.15

(ExpectedConditions

-0.14

etas

-0.14

ÐºÑĤ

-0.14

ÐµÑĩÐµÐ½Ð¸Ðµ

-0.14

ayas

-0.14

otas

-0.13

abr

-0.13

irie

-0.13

_SWITCH

-0.13

POSITIVE LOGITS

isque

0.17

ulace

0.15

ucci

0.15

Verb

0.15

ilon

0.15

onte

0.14

Ã²a

0.14

titleLabel

0.14

diff

0.14

gram

0.14

Activations Density 0.013%

references to data structures and arrays in programming

No Comments

No Known Activations