INDEX

Explanations

the presence of the word "Additional" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

lio

-0.17

ego

-0.16

places

-0.15

ÑĢÐ°Ð¹

-0.15

æł·çļĦ

-0.14

drawing

-0.14

trap

-0.14

Å¡k

-0.14

è±

-0.14

vak

-0.14

POSITIVE LOGITS

ordinary

0.23

mente

0.22

ordin

0.22

/sub

0.22

0.21

endum

0.21

/new

0.20

CTION

0.19

tion

0.18

 layers

0.18

Activations Density 0.019%

the presence of the word "Additional" in various contexts

No Comments

No Known Activations