INDEX

Explanations

formatted string patterns and placeholders in code

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

nt

-0.18

eniz

-0.15

 marginal

-0.15

sec

-0.15

sted

-0.15

che

-0.14

iron

-0.14

enal

-0.14

POSITIVE LOGITS

DataStream

0.19

aley

0.15

ogne

0.14

IID

0.14

iphy

0.14

uga

0.14

 licensors

0.14

ylon

0.14

Ñĳ

0.14

Ð¸Ð¹

0.14

Activations Density 0.006%

formatted string patterns and placeholders in code

No Comments

No Known Activations