INDEX

Explanations

phrases indicating ongoing problems or unresolved issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 Rough

-0.17

xef

-0.16

frau

-0.15

vere

-0.14

urette

-0.14

ccb

-0.14

riba

-0.14

eru

-0.14

erner

-0.13

leh

-0.13

POSITIVE LOGITS

 still

0.25

 Still

0.21

still

0.19

è¿ĺæĺ¯

0.19

Still

0.18

 STILL

0.17

 ainda

0.17

olland

0.16

-ie

0.15

.gg

0.15

Activations Density 0.249%

phrases indicating ongoing problems or unresolved issues

No Comments

No Known Activations