INDEX

Explanations

references to governmental or organizational initiatives and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

atters

-0.16

classCallCheck

-0.15

bens

-0.14

meg

-0.14

/Delete

-0.13

prus

-0.13

estar

-0.13

_eq

-0.12

ãĥ¥

-0.12

ulfilled

-0.12

POSITIVE LOGITS

urette

0.17

ibal

0.15

 lamb

0.15

uard

0.15

akov

0.14

onn

0.14

¯

0.14

 ours

0.14

acios

0.14

 Tiger

0.13

Activations Density 0.100%

references to governmental or organizational initiatives and events

No Comments

No Known Activations