INDEX

Explanations

tokens or phrases related to names and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ialis

-0.16

endency

-0.15

otti

-0.15

-0.14

NET

-0.14

etur

-0.14

.netty

-0.14

çĻ

-0.14

pto

-0.14

POSITIVE LOGITS

QRS

0.15

anter

0.14

 minimum

0.14

.setCode

0.14

 unless

0.14

anou

0.13

 springfox

0.13

.Id

0.13

IDD

0.13

Lady

0.13

Activations Density 0.152%

tokens or phrases related to names and organizations

No Comments

No Known Activations