INDEX

Explanations

discussions surrounding general topics or themes

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

inha

-0.17

 Dort

-0.16

nder

-0.14

/Foundation

-0.14

rok

-0.14

 bubb

-0.13

imore

-0.13

 Dodd

-0.13

ĶåĽŀ

-0.13

.GUI

-0.13

POSITIVE LOGITS

itzer

0.17

utzer

0.17

ptom

0.16

ecal

0.16

.SaveChangesAsync

0.15

ulk

0.15

 Shame

0.14

ÑĮÑİ

0.14

AGR

0.14

ARED

0.13

Activations Density 0.028%

discussions surrounding general topics or themes

No Comments

No Known Activations