INDEX

Explanations

terms related to rankings and positions in competitive contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

stdarg

-0.17

 ÙĤÙĨ

-0.15

auce

-0.14

å¼ĺ

-0.14

	throws

-0.14

Ð½Ð¾ÑģÑĤ

-0.14

ora

-0.14

ameda

-0.14

 /**<

-0.14

.Screen

-0.14

POSITIVE LOGITS

0.16

outil

0.16

 bullet

0.15

 heading

0.14

Å¡k

0.14

pped

0.14

 Hath

0.14

 rating

0.13

top

0.13

 weekly

0.13

Activations Density 0.011%

terms related to rankings and positions in competitive contexts

No Known Activations