INDEX

Explanations

references to specific individuals, names, or unique identifiers 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

.Dataset

-0.15

Ú©Ø´

-0.15

 dÃ©t

-0.14

Å¡ov

-0.14

 Crawford

-0.13

cess

-0.13

/^(

-0.13

Ð°ÑĪÐ°

-0.13

sin

-0.13

oks

-0.13

POSITIVE LOGITS

ãĥ¼ãĥĨãĤ£

0.16

upal

0.16

ENA

0.16

Cancelable

0.15

uarios

0.15

beeld

0.14

.NewRequest

0.14

Ĥæķ°

0.14

adel

0.14

Å®

0.14

Activations Density 0.066%

references to specific individuals, names, or unique identifiers in various contexts

No Comments

No Known Activations