INDEX

Explanations

phrases indicating proportions or divisions of entities

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

ueva

-0.18

opers

-0.18

 overnight

-0.16

inery

-0.16

ORK

-0.15

chrift

-0.15

alla

-0.15

of

-0.15

obra

-0.15

POSITIVE LOGITS

.scalablytyped

0.18

ekil

0.15

EdgeInsets

0.14

OnClickListener

0.14

 ruku

0.14

roke

0.14

Scrollbar

0.14

gregar

0.13

plit

0.13

uckles

0.13

Activations Density 0.281%

phrases indicating proportions or divisions of entities

No Comments

No Known Activations