INDEX

Explanations

phrases or questions that inquire about the functioning or effectiveness of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.19

-0.16

lit

-0.16

oland

-0.15

erais

-0.15

uya

-0.15

lif

-0.15

ort

-0.15

irut

-0.14

POSITIVE LOGITS

rious

0.15

ATUS

0.15

pcl

0.15

iÄįe

0.15

Å

0.15

Î½ÎµÎ¹

0.14

.:

0.14

 Bour

0.14

-Smith

0.14

Ð´ÑĸÐ»

0.13

Activations Density 0.021%

phrases or questions that inquire about the functioning or effectiveness of something

No Comments

No Known Activations