INDEX

Explanations

descriptions of actions and processes in a timeline or sequential context

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

 begin

-0.85

 begins

-0.77

 beginning

-0.76

begin

-0.75

 Begin

-0.71

 began

-0.70

å¼Ģå§ĭ

-0.70

 begun

-0.69

 starts

-0.66

 Begins

-0.65

POSITIVE LOGITS

0.15

 endpoint

0.14

.advance

0.14

íĦ

0.14

chÃ¡z

0.14

 advance

0.13

åĶ

0.13

 Endpoint

0.13

::$_

0.13

ÄĽl

0.13

Activations Density 0.213%

descriptions of actions and processes in a timeline or sequential context

No Comments

No Known Activations