INDEX

Explanations

phrases indicating required minimums or conditions in various 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

Not in Any Lists

No Comments

Negative Logits

-scalable

-0.16

loff

-0.15

 ÐĿÐ°Ð·

-0.15

maxLength

-0.14

ona

-0.14

XObject

-0.14

noinspection

-0.13

imax

-0.13

DBG

-0.13

elige

-0.13

POSITIVE LOGITS

 minimum

0.28

 Minimum

0.27

Minimum

0.23

minimum

0.23

 minim

0.19

_minimum

0.17

arta

0.17

 ÎķÏĢ

0.17

 Floor

0.16

Min

0.16

Activations Density 0.048%

phrases indicating required minimums or conditions in various contexts

No Comments

No Known Activations