INDEX

Explanations

phrases that indicate permission or enablement for actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

utherland

-0.15

RIPT

-0.14

cury

-0.14

uf

-0.14

å¸®

-0.14

Î¸ÎµÏģ

-0.14

UF

-0.14

ventus

-0.13

ulfilled

-0.13

 pomoc

-0.13

POSITIVE LOGITS

us

0.31

you

0.20

 easy

0.17

ffects

0.16

us

0.16

him

0.16

swer

0.16

 easily

0.15

 ÑģÐ¾Ð±Ð¾Ð¹

0.15

 them

0.14

Activations Density 0.057%

phrases that indicate permission or enablement for actions or processes

No Comments

No Known Activations