INDEX

Explanations

nested parentheses and their structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oldur

-0.18

xffffffff

-0.15

ebin

-0.14

omitempty

-0.14

iveau

-0.13

timeofday

-0.13

 Prostitutas

-0.13

boz

-0.13

ASSERT

-0.12

ÅĤaw

-0.12

POSITIVE LOGITS

ses

0.15

ipp

0.14

/how

0.13

 quot

0.13

 Chip

0.13

usch

0.12

ovic

0.12

iston

0.12

 they

0.12

 Horton

0.12

Activations Density 0.078%

nested parentheses and their structures

No Comments

No Known Activations