INDEX

Explanations

references to the Google brand within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÑģÐºÐ°

-0.16

usta

-0.15

ku

-0.14

 Brew

-0.14

Cy

-0.14

rens

-0.14

ÅĻ

-0.14

lation

-0.14

 Bran

-0.14

icken

-0.14

POSITIVE LOGITS

.common

0.29

.inject

0.23

.api

0.23

inject

0.22

Inject

0.22

.gson

0.22

 COMMON

0.21

/common

0.20

 common

0.19

\common

0.19

Activations Density 0.006%

references to the Google brand within a technical context

No Comments

No Known Activations