INDEX

Explanations

references to quantities and time-related measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Href

-0.14

gabe

-0.14

-0.13

æĻ

-0.13

 separat

-0.13

MMdd

-0.13

lif

-0.12

ãģķãĤĵãģĮ

-0.12

Sun

-0.12

omm

-0.12

POSITIVE LOGITS

nbsp

0.17

.showError

0.15

raquo

0.15

Ð±ÑĥÐ´ÑĮ

0.15

oro

0.15

Ð¾Ð¸ÑĤ

0.15

apos

0.15

ÑĥÑĩÐ°

0.15

UTE

0.14

iros

0.14

Activations Density 0.156%

references to quantities and time-related measures

No Comments

No Known Activations