INDEX

Explanations

phrases related to receiving, obtaining, or achieving outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ãĥ¼ãĥĸ

-0.15

 æħ

-0.15

ackages

-0.14

rowable

-0.14

_Debug

-0.14

ittal

-0.14

ska

-0.14

ilos

-0.14

illis

-0.14

glas

-0.14

POSITIVE LOGITS

rid

0.29

 hold

0.23

Rid

0.21

 benef

0.20

 into

0.20

ÑĤÐ¸Ðº

0.19

rid

0.19

 chance

0.18

 benefited

0.18

 success

0.17

Activations Density 0.062%

phrases related to receiving, obtaining, or achieving outcomes

No Comments

No Known Activations