INDEX

Explanations

numeric values or statistics related to measurements or percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ãģĦãĤĭ

-0.19

lane

-0.17

iating

-0.16

 Caldwell

-0.16

ially

-0.15

aney

-0.15

alus

-0.15

ial

-0.15

ooke

-0.15

.au

-0.14

POSITIVE LOGITS

ingly

0.19

bots

0.16

housing

0.16

phere

0.15

 nghiá»ĩm

0.15

åĽ£

0.15

ãĤĬãģ¨

0.15

ture

0.15

reate

0.14

ford

0.14

Activations Density 0.131%

numeric values or statistics related to measurements or percentages

No Comments

No Known Activations