INDEX

Explanations

negative phrases or contractions indicating impossibility or prohibition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iais

-0.18

asion

-0.18

anske

-0.15

-0.14

illi

-0.14

STYPE

-0.14

ival

-0.14

.DropDown

-0.13

POSITIVE LOGITS

zon

0.17

CEE

0.15

urtle

0.15

ãĤ¶ãĥ¼

0.14

ches

0.14

');?>

0.14

INO

0.13

 hormone

0.13

 hemp

0.13

ilda

0.13

Activations Density 0.043%

negative phrases or contractions indicating impossibility or prohibition

No Comments

No Known Activations