INDEX

Explanations

references to specific entities or items, particularly in the context of guidelines or structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

usting

-0.17

udge

-0.17

-0.14

usted

-0.14

 drive

-0.14

 regards

-0.13

iciar

-0.13

 Drive

-0.13

Gi

-0.13

 compound

-0.13

POSITIVE LOGITS

flix

0.16

ASF

0.16

orre

0.15

.encoding

0.15

Ascii

0.15

Wunused

0.15

aten

0.14

uppe

0.14

æĸ¹åĲĳ

0.14

rieb

0.14

Activations Density 0.138%

references to specific entities or items, particularly in the context of guidelines or structures

No Comments

No Known Activations