INDEX

Explanations

phrases that indicate conditions or criteria, particularly involving limits and expectations

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

Not in Any Lists

No Comments

Negative Logits

gil

-0.16

ansi

-0.15

Ð»ÐµÐ¶

-0.14

 Ù¾Ø§ÛĮÙĩ

-0.13

ATEST

-0.13

rello

-0.13

 stamina

-0.13

 Bloss

-0.13

rella

-0.13

stag

-0.13

POSITIVE LOGITS

 necessarily

0.19

okies

0.16

ynes

0.15

evin

0.15

elow

0.15

inoa

0.14

owy

0.14

 Ð¾Ð±ÑıÐ·Ð°ÑĤÐµÐ»ÑĮÐ½Ð¾

0.14

ativa

0.13

 Lambert

0.13

Activations Density 0.052%

phrases that indicate conditions or criteria, particularly involving limits and expectations

No Comments

No Known Activations