INDEX

Explanations

keywords related to academic references and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.writ

-0.16

orris

-0.16

ropri

-0.15

usi

-0.15

ambi

-0.15

reative

-0.14

reten

-0.14

ropic

-0.14

ersonic

-0.14

retweeted

-0.14

POSITIVE LOGITS

ABL

0.17

vig

0.15

ipo

0.15

yne

0.15

meer

0.15

 shedding

0.14

instein

0.14

ifecycle

0.14

lt

0.13

(moment

0.13

Activations Density 0.627%

keywords related to academic references and citations

No Comments

No Known Activations