INDEX

Explanations

phrases that convey relationships and connections between concepts or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

iec

-0.14

#ab

-0.14

Ø§ØµÙĦÙĩ

-0.13

tae

-0.13

imli

-0.13

burgh

-0.13

 Neck

-0.13

izik

-0.13

PT

-0.13

PointCloud

-0.13

POSITIVE LOGITS

/or

0.18

acs

0.15

Gear

0.14

.cgi

0.14

atory

0.14

 understanding

0.14

wan

0.13

 æ´

0.13

 downright

0.13

 indeed

0.13

Activations Density 0.381%

phrases that convey relationships and connections between concepts or elements

No Comments

No Known Activations