INDEX

Explanations

phrases and expressions indicating past experiences or continuous states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

dere

-0.15

Ø´Ø¯

-0.15

(^

-0.15

chet

-0.14

ÏĦÎŃ

-0.14

oho

-0.14

atatype

-0.14

ÃŃcia

-0.14

eson

-0.13

egasus

-0.13

POSITIVE LOGITS

 lately

0.34

 recently

0.24

 since

0.24

 recent

0.20

recent

0.19

since

0.19

ä»¥æĿ¥

0.19

Recently

0.18

 Recently

0.17

 ÙħÙĨØ°

0.17

Activations Density 0.374%

phrases and expressions indicating past experiences or continuous states of being

No Comments

No Known Activations