INDEX

Explanations

the ending of the word "ent"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.16

erdem

-0.16

ryn

-0.15

gili

-0.14

ventas

-0.14

±ä¹Ĳ

-0.14

ryo

-0.14

ycl

-0.14

throp

-0.14

leys

-0.13

POSITIVE LOGITS

enu

0.17

Ð»ÑĥÐ³

0.16

.flat

0.15

ÄĽr

0.15

à¥Ģà¤Ł

0.15

maid

0.14

 Midnight

0.14

Ł

0.14

/TR

0.14

erner

0.14

Activations Density 0.000%

the ending of the word "ent"

No Comments

No Known Activations