INDEX

Explanations

the occurrence of the word "two."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ilst

-0.18

 Chance

-0.16

.setResult

-0.15

Chance

-0.14

Ã©g

-0.14

 Milf

-0.14

à¥Ģà¤ķà¤°à¤£

-0.14

.frequency

-0.14

FRE

-0.14

ipple

-0.14

POSITIVE LOGITS

 Stuff

0.15

jing

0.15

aload

0.14

ÅĤa

0.13

lix

0.13

lug

0.13

ondo

0.13

icity

0.13

DF

0.13

Activations Density 0.058%

the occurrence of the word "two."

No Comments

No Known Activations