INDEX

Explanations

phrases indicative of statistical data or numerical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ÏĦÎ¶

-0.17

igu

-0.15

mand

-0.15

ota

-0.15

okol

-0.14

ç°

-0.14

ercul

-0.14

iem

-0.14

ieres

-0.14

ÑĥÑİÑĤÑģÑı

-0.14

POSITIVE LOGITS

ewis

0.19

 pylint

0.16

 Cush

0.15

OLS

0.14

 Deng

0.14

0.13

tw

0.13

ished

0.13

 Ø§ÙĦÙĪØµ

0.13

aley

0.13

Activations Density 0.021%

phrases indicative of statistical data or numerical information

No Comments

No Known Activations