INDEX

Explanations

instances of the word "attach" and its derivatives

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

-ÑĤÐ¾

-0.18

ÑĢÐ°Ð²

-0.16

stras

-0.16

rie

-0.15

erer

-0.15

stral

-0.15

stown

-0.15

usal

-0.15

Equivalent

-0.15

POSITIVE LOGITS

ments

0.25

ement

0.23

/embed

0.22

ements

0.21

Ã©

0.20

-det

0.19

ment

0.19

Detach

0.18

ivity

0.18

.Attach

0.17

Activations Density 0.023%

instances of the word "attach" and its derivatives

No Comments

No Known Activations