INDEX

Explanations

phrases that emphasize significant or noteworthy reports or announcements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

aved

-0.15

 ever

-0.15

uguay

-0.15

 JÃ¡

-0.15

amik

-0.15

ankan

-0.14

 Madd

-0.14

Vik

-0.14

 giant

-0.13

POSITIVE LOGITS

olare

0.15

 DropIndex

0.15

êµ°ìļĶ

0.13

 Snape

0.13

.Logf

0.13

ãĥªãĥ³ãĤ°

0.13

 Ð²Ð¾ÑĢ

0.13

zb

0.13

ocker

0.13

âĢ¦âĢ¦↵↵

0.12

Activations Density 0.191%

phrases that emphasize significant or noteworthy reports or announcements

No Comments

No Known Activations