INDEX

Explanations

specific attributes, options, and elements related to various categories and contexts

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

.tell

-0.16

igate

-0.14

shan

-0.14

RuleContext

-0.14

AML

-0.14

agma

-0.14

iners

-0.14

GuidId

-0.14

hunt

-0.13

educt

-0.13

POSITIVE LOGITS

we

0.27

 they

0.26

 exactly

0.23

it

0.21

he

0.20

 might

0.20

you

0.19

she

0.19

soever

0.18

/if

0.17

Activations Density 0.086%

specific attributes, options, and elements related to various categories and contexts

No Comments

No Known Activations