INDEX

Explanations

phrases indicating a desire for knowledge or seeking information

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

Ð¾Ð·Ð²

-0.16

 æ¨

-0.15

avec

-0.15

strand

-0.14

(æĹ¥

-0.14

upert

-0.14

adar

-0.14

onde

-0.14

ieg

-0.14

intl

-0.14

POSITIVE LOGITS

GetType

0.15

ellig

0.15

0.14

DIRECT

0.14

Bid

0.14

çļĦè¯Ŀ

0.14

 learn

0.14

0.13

omba

0.13

 ÅĻÃŃj

0.13

Activations Density 0.052%

phrases indicating a desire for knowledge or seeking information

No Comments

No Known Activations