INDEX

Explanations

quotations or attributions in the text

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

elf

-0.17

.usage

-0.16

avs

-0.16

uhn

-0.14

leanup

-0.14

 à¤®à¤°

-0.14

 skeleton

-0.13

estr

-0.13

POSITIVE LOGITS

_initializer

0.15

ancel

0.15

fern

0.15

ivan

0.14

abwe

0.14

Coordinator

0.14

itaire

0.14

rex

0.14

edia

0.14

GBK

0.14

Activations Density 0.104%

quotations or attributions in the text

No Comments

No Known Activations