INDEX

Explanations

terms related to practical details and complexities

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

/apt

-0.17

 unto

-0.16

VS

-0.16

legg

-0.16

riors

-0.15

icode

-0.14

_RST

-0.14

ÅĻiv

-0.14

allon

-0.14

Ã¦k

-0.14

POSITIVE LOGITS

 aspects

0.25

 aspect

0.23

 Aspect

0.22

pects

0.20

Aspect

0.18

 involved

0.18

aspect

0.18

 behind

0.18

olley

0.17

of

0.17

Activations Density 0.141%

terms related to practical details and complexities

No Comments

No Known Activations