INDEX

Explanations

highlights of significant actions and ideas within a textual context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

BarButton

-0.15

 latter

-0.15

-0.14

amp

-0.14

 Serge

-0.14

iaux

-0.14

 Sphinx

-0.14

orea

-0.14

voj

-0.13

val

-0.13

POSITIVE LOGITS

 essentially

0.17

 Ú¯Ø±Ø¯ÛĮØ¯

0.16

 basically

0.15

ç¼ĺ

0.15

.bpm

0.15

 (!((

0.14

sink

0.14

Basically

0.14

Î´Î·

0.14

ãĤ¹ãĤ³

0.14

Activations Density 0.101%

highlights of significant actions and ideas within a textual context

No Comments

No Known Activations