INDEX

Explanations

specific technical terms and designations related to high technology or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

hol

-0.18

ron

-0.18

ries

-0.17

allen

-0.17

ric

-0.16

richt

-0.16

usch

-0.16

ran

-0.15

rad

-0.15

rid

-0.15

POSITIVE LOGITS

Ð¾ÑģÑĮ

0.16

Î³Î¼Î±

0.15

urtle

0.15

er

0.15

inction

0.15

ystone

0.15

terdam

0.15

Ð°Ð²Ð°

0.15

COND

0.14

CHK

0.14

Activations Density 0.026%

specific technical terms and designations related to high technology or scientific contexts

No Comments

No Known Activations