INDEX

Explanations

references to organizations, institutions, or locations associated with community and education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

erek

-0.17

inds

-0.15

erval

-0.15

eration

-0.14

of

-0.14

pheric

-0.13

eya

-0.13

/her

-0.13

dere

-0.13

uito

-0.13

POSITIVE LOGITS

ÎºÏģÎ¹

0.14

imizer

0.14

\Builder

0.14

/Open

0.14

emann

0.14

etrain

0.14

MMdd

0.13

/H

0.13

.Destroy

0.13

TemplateName

0.13

Activations Density 0.211%

references to organizations, institutions, or locations associated with community and education

No Comments

No Known Activations