INDEX

Explanations

terms related to complex interactions and phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

er

-0.19

iston

-0.17

posites

-0.16

erca

-0.15

ãģĦãĤĭ

-0.15

kest

-0.15

ishes

-0.15

ieten

-0.15

clearfix

-0.15

########

-0.15

POSITIVE LOGITS

ech

0.24

roph

0.21

uary

0.20

utorial

0.20

unes

0.19

ending

0.19

ecs

0.19

urn

0.19

unity

0.19

issue

0.19

Activations Density 0.078%

terms related to complex interactions and phenomena

No Comments

No Known Activations