INDEX

Explanations

references to significant events or milestones related to specific years, particularly in the context of popular culture or media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

brero

-0.16

inha

-0.16

 nast

-0.15

auge

-0.15

intage

-0.15

cratch

-0.14

 Zodiac

-0.14

Ð¾ÑĢÐµ

-0.14

ÑĥÐºÐ°

-0.14

iffe

-0.14

POSITIVE LOGITS

ATAR

0.17

umn

0.16

 Schwartz

0.15

Bes

0.14

olerance

0.14

tle

0.14

aze

0.13

altar

0.13

 Schneider

0.13

 táºŃn

0.13

Activations Density 0.019%

references to significant events or milestones related to specific years, particularly in the context of popular culture or media

No Comments

No Known Activations