INDEX

Explanations

phrases that connect ideas or concepts, often emphasizing relationships or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ensibly

-0.17

 questionable

-0.16

 dubious

-0.15

uC

-0.15

 tslib

-0.14

 eventual

-0.14

_CONV

-0.14

 other

-0.13

 mere

-0.13

 countless

-0.13

POSITIVE LOGITS

yet

0.20

yet

0.19

 full

0.17

alive

0.15

 definitely

0.15

 verg

0.15

ieber

0.14

 Ð»Ð¸ÑĪ

0.14

á»ĵi

0.14

Full

0.14

Activations Density 0.366%

phrases that connect ideas or concepts, often emphasizing relationships or comparisons

No Comments

No Known Activations