INDEX

Explanations

references to theatrical plays and performance-related terms

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

assi

-0.15

hood

-0.15

ogn

-0.15

.mj

-0.15

assin

-0.15

 Mens

-0.14

åĢ

-0.14

ÑĥÐºÐ°

-0.14

MMdd

-0.14

OutOfBoundsException

-0.14

POSITIVE LOGITS

isch

0.20

ended

0.14

bench

0.14

ruk

0.14

Ø§Ø¦ÙĤ

0.13

uffer

0.13

wright

0.13

 shaders

0.13

omo

0.13

heed

0.13

Activations Density 0.097%

references to theatrical plays and performance-related terms

No Comments

No Known Activations