INDEX

Explanations

phrases that indicate relationships or connections between different elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

tics

-0.20

zin

-0.18

Å¾enÃŃ

-0.17

anco

-0.16

ãĥ³ãĥĲ

-0.15

orman

-0.14

.analytics

-0.14

eter

-0.14

Äħ

-0.14

POSITIVE LOGITS

chaft

0.17

ëĲĺëĬĶ

0.14

iment

0.14

DevExpress

0.14

alez

0.14

phan

0.14

/uploads

0.14

ãĥ¼ãĥĦ

0.14

entin

0.14

adaÅŁ

0.14

Activations Density 0.034%

phrases that indicate relationships or connections between different elements

No Comments

No Known Activations