INDEX

Explanations

specific names and terms related to authors and scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-0.15

å¤§äºº

-0.14

weets

-0.14

 Hispan

-0.14

\\/

-0.13

elligence

-0.13

Ð¾Ð¼ÐµÐ½

-0.13

æ·

-0.13

áº§m

-0.12

/to

-0.12

POSITIVE LOGITS

0.19

Jr

0.17

(auth

0.17

0.16

amd

0.16

III

0.16

ÌĢ

0.15

eds

0.15

 equal

0.15

Activations Density 0.040%

specific names and terms related to authors and scientific research

No Comments

No Known Activations