INDEX

Explanations

references to answers and their significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

chet

-0.17

sus

-0.16

igi

-0.16

unky

-0.16

quez

-0.16

Ø®Ø§ÙĨÙĩ

-0.15

audi

-0.15

istributed

-0.15

Ø±Ø§ÙĤ

-0.14

(DbContext

-0.14

POSITIVE LOGITS

asp

0.20

ing

0.17

able

0.17

/address

0.15

.answer

0.15

phone

0.15

ative

0.15

(answer

0.15

al

0.15

ans

0.15

Activations Density 0.038%

references to answers and their significance in various contexts

No Comments

No Known Activations