INDEX

Explanations

abbreviations and acronyms related to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

es

-0.20

esco

-0.19

esh

-0.17

esian

-0.16

fus

-0.16

 coax

-0.16

cop

-0.15

áº»

-0.15

heimer

-0.15

ansom

-0.15

POSITIVE LOGITS

etyl

0.20

uum

0.17

rosse

0.16

obi

0.16

dac

0.15

illus

0.15

 Prescott

0.15

.Pool

0.15

chers

0.15

rylic

0.14

Activations Density 0.051%

abbreviations and acronyms related to organizations or entities

No Comments

No Known Activations