INDEX

Explanations

expressions of capability and accomplishment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 ç¨

-0.17

-0.15

ÐµÐ´

-0.15

ohen

-0.14

ually

-0.14

 Stokes

-0.14

.ToDateTime

-0.14

-0.13

ÑĦÐ¾ÑĢÐ¼Ð¸

-0.13

POSITIVE LOGITS

 substance

0.20

 personality

0.20

 Personality

0.18

 everything

0.18

egl

0.18

 legs

0.15

eson

0.15

 Substance

0.15

eba

0.14

 æ¯

0.14

Activations Density 0.150%

expressions of capability and accomplishment

No Comments

No Known Activations