INDEX

Explanations

references to the concept of "status" in various contexts

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

ewe

-0.18

strict

-0.15

Î²Î¿

-0.14

zos

-0.14

LOT

-0.14

igham

-0.14

isto

-0.14

ãĤ¤ãĤ¯

-0.14

Storm

-0.14

thon

-0.13

POSITIVE LOGITS

quo

0.27

istical

0.19

ngr

0.17

ses

0.17

sed

0.16

yonel

0.16

quez

0.16

=status

0.16

(Status

0.15

.heroku

0.15

Activations Density 0.020%

references to the concept of "status" in various contexts

No Comments

No Known Activations