INDEX

Explanations

information-seeking phrases and expressions about awareness and understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

undle

-0.15

ople

-0.14

Ø¬Ùĩ

-0.14

asse

-0.14

 Whoever

-0.13

.heap

-0.13

 personn

-0.13

 Ð½ÐµÐ³Ð¾

-0.13

optim

-0.13

è¾ŀ

-0.13

POSITIVE LOGITS

 which

0.30

 whether

0.27

if

0.27

 exactly

0.25

which

0.23

whether

0.19

 precisely

0.19

if

0.18

 Which

0.18

 Rough

0.18

Activations Density 0.117%

information-seeking phrases and expressions about awareness and understanding

No Comments

No Known Activations