INDEX

Explanations

ellipses and indicators for continuation in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

esen

-0.15

leur

-0.15

ãĤ«ãĥ¼

-0.15

idan

-0.15

-0.14

oub

-0.14

ONGO

-0.14

.scalablytyped

-0.14

eler

-0.14

ãĤ»ãĥ³

-0.14

POSITIVE LOGITS

lue

0.17

oard

0.15

hai

0.15

ÏģÎ¹Î±

0.14

oltip

0.14

zd

0.14

Ð¾Ðµ

0.14

æŀ¶

0.14

iol

0.14

-io

0.14

Activations Density 0.048%

ellipses and indicators for continuation in text

No Comments

No Known Activations