INDEX

Explanations

technical jargon related to software development and configuration

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

New Auto-Interp

Configuration

fnlp/Llama3_1-8B-Base-LXM-8x/Llama3_1-8B-Base-L22M-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_mlp_out

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

abit

-0.16

uz

-0.16

 Inst

-0.16

áº£o

-0.16

ãĥ¼ãĥ¬

-0.15

inst

-0.15

DataURL

-0.15

ukt

-0.14

Inst

-0.14

Spin

-0.14

POSITIVE LOGITS

 grad

0.17

ichten

0.17

 gradu

0.17

grad

0.15

rel

0.15

 Grad

0.15

athy

0.14

ooke

0.14

_grad

0.14

Activations Density 0.120%

technical jargon related to software development and configuration

No Comments

No Known Activations