INDEX

Explanations

expressions of positive feedback or praise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 exped

-0.16

Callbacks

-0.15

Gow

-0.15

,exports

-0.14

 curs

-0.14

odega

-0.14

stroy

-0.13

 synd

-0.13

 Notify

-0.13

 discrimin

-0.13

POSITIVE LOGITS

edList

0.17

ffee

0.15

andest

0.15

mgr

0.15

enschaft

0.14

_bug

0.14

ÑģÑĤÐ¸ÑĤ

0.14

iid

0.14

opia

0.14

-navbar

0.14

Activations Density 0.072%

expressions of positive feedback or praise

No Comments

No Known Activations