INDEX

Explanations

references to locations and time spent in various places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ReadStream

-0.17

ãĥ³ãĥĲ

-0.16

bens

-0.15

DEFINE

-0.15

rides

-0.15

å¿Ĺ

-0.15

rav

-0.15

ingroup

-0.14

swire

-0.14

itra

-0.14

POSITIVE LOGITS

 weekend

0.16

 conferences

0.16

cratch

0.16

 Conference

0.15

AR

0.15

ÐĶÐļ

0.15

.COL

0.15

 Relative

0.14

 ÐºÐ¾Ð»ÑĮ

0.14

 ÑĤÐ°Ð¼

0.14

Activations Density 0.148%

references to locations and time spent in various places

No Comments

No Known Activations