INDEX

Explanations

references to places or proper names, particularly variations of "Jer"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

.TabStop

-0.16

sz

-0.15

vos

-0.15

 Invest

-0.14

èµ·æĿ¥

-0.14

/operators

-0.14

splash

-0.14

arin

-0.13

 Ø§ÛĮØ³Øª

-0.13

/tos

-0.13

POSITIVE LOGITS

usalem

0.24

icho

0.21

Ã´me

0.19

usal

0.18

assic

0.17

enser

0.17

main

0.17

asic

0.17

Ø¯Ø¯

0.17

Mess

0.16

Activations Density 0.014%

references to places or proper names, particularly variations of "Jer"

No Comments

No Known Activations