INDEX

Explanations

references to standards and regulations 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.infinity

-0.17

uben

-0.17

chner

-0.15

ordan

-0.15

ocular

-0.15

eyh

-0.15

pee

-0.15

dar

-0.15

age

-0.15

à¤łà¤¨

-0.15

POSITIVE LOGITS

ised

0.28

-issue

0.25

-setting

0.21

ize

0.20

izes

0.20

ization

0.19

 deviation

0.18

ized

0.18

.Std

0.18

izing

0.18

Activations Density 0.026%

references to standards and regulations in various contexts

No Comments

No Known Activations