INDEX

Explanations

prepositions and their usage in context

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

aches

-0.18

occo

-0.17

oul

-0.15

æ¸

-0.15

urs

-0.15

owe

-0.15

azar

-0.14

$__

-0.14

MBProgressHUD

-0.14

ges

-0.14

POSITIVE LOGITS

 tier

0.17

 Tier

0.14

seys

0.14

esa

0.14

 Serif

0.14

WithError

0.13

roys

0.13

ãĥ£

0.13

ÏĦÎ¿Î»

0.13

allen

0.13

Activations Density 0.039%

prepositions and their usage in context

No Comments

No Known Activations