INDEX

Explanations

references to notable figures and their attributes in cultural or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

eping

-0.19

iper

-0.16

nila

-0.14

ÄĽr

-0.14

igans

-0.14

 foul

-0.14

tring

-0.13

elerik

-0.13

Ð¾Ð²

-0.13

 Reese

-0.13

POSITIVE LOGITS

(ST

0.26

st

0.25

.st

0.23

/st

0.23

(st

0.23

ST

0.22

St

0.21

St

0.21

,st

0.20

.St

0.20

Activations Density 0.202%

references to notable figures and their attributes in cultural or academic contexts

No Comments

No Known Activations