INDEX

Explanations

references to the word "Pad" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addtogroup

-0.17

ubern

-0.16

ILES

-0.16

ainment

-0.16

prÃ¼

-0.15

ariat

-0.15

oord

-0.14

coles

-0.14

Î¯Î´

-0.14

ç¾©

-0.14

POSITIVE LOGITS

-pad

0.24

.pad

0.23

Pad

0.23

pad

0.21

locks

0.20

ernal

0.19

locking

0.19

PAD

0.19

lock

0.19

ua

0.18

Activations Density 0.014%

references to the word "Pad" in various contexts

No Comments

No Known Activations