INDEX

Explanations

references to the name "Pierre."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

oline

-0.18

oi

-0.17

ymoon

-0.16

vÅ¯

-0.15

lope

-0.15

SingleOrDefault

-0.15

.DriverManager

-0.15

ãĥ©ãĤ¤ãĥ³

-0.15

rien

-0.15

_EOL

-0.15

POSITIVE LOGITS

æ¿

0.17

edback

0.17

asso

0.16

aldi

0.15

Lav

0.15

allas

0.15

ÏĦÎ¹Ïĥ

0.14

erne

0.14

(version

0.14

LS

0.14

Activations Density 0.005%

references to the name "Pierre."

No Known Activations