INDEX

Explanations

terms related to difficulty, hardship, or challenges faced by individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

cus

-0.15

 strav

-0.15

etur

-0.14

åŃĺæ¡£

-0.14

oom

-0.14

.Panel

-0.14

eu

-0.13

ÙħØª

-0.13

asca

-0.13

MENT

-0.13

POSITIVE LOGITS

 might

0.28

 Might

0.24

might

0.22

 against

0.21

-hard

0.21

val

0.20

 hard

0.19

mag

0.19

 harder

0.18

-fit

0.18

Activations Density 0.019%

terms related to difficulty, hardship, or challenges faced by individuals or groups

No Comments

No Known Activations