INDEX

Explanations

formatting elements related to data representation or query expressions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

omi

-0.17

ordion

-0.17

ughters

-0.16

nger

-0.16

erson

-0.15

sup

-0.15

 Bach

-0.14

apy

-0.14

urnished

-0.14

rylic

-0.14

POSITIVE LOGITS

#ab

0.15

 Dungeon

0.15

0.14

Aub

0.14

UIF

0.14

ê°Ī

0.14

Decoder

0.14

UA

0.14

nego

0.13

rok

0.13

Activations Density 0.010%

formatting elements related to data representation or query expressions

No Known Activations