INDEX

Explanations

features or segments detailing new or special content in writings

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

Not in Any Lists

No Comments

Negative Logits

ersen

-0.15

ens

-0.15

ers

-0.13

lineno

-0.13

oria

-0.13

-Key

-0.13

 warranty

-0.13

æ´

-0.13

POSITIVE LOGITS

ãĤ·ãĥªãĥ¼ãĤº

0.20

 series

0.18

'gc

0.18

irket

0.17

utton

0.16

 feature

0.16

Recovered

0.15

azio

0.15

Disappear

0.15

ç³»åĪĹ

0.15

Activations Density 0.082%

features or segments detailing new or special content in writings

No Comments

No Known Activations