INDEX

Explanations

specific numerical sequences or patterns that appear frequently

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

edly

-0.22

ucker

-0.17

iras

-0.15

 jadx

-0.15

acie

-0.15

ucket

-0.14

adesh

-0.14

PTS

-0.14

resco

-0.14

razier

-0.14

POSITIVE LOGITS

wil

0.16

ven

0.15

à¸ĩà¸²à¸Ļ

0.15

oyer

0.15

çĿĽ

0.14

gth

0.14

-ÑĤÐ¾

0.14

Ø§Ø³ÛĮ

0.14

.FIELD

0.13

Activations Density 0.008%

specific numerical sequences or patterns that appear frequently

No Comments

No Known Activations