INDEX

Explanations

instances of the word "And" in various contexts

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

irl

-0.15

teri

-0.15

à¸

-0.15

cta

-0.14

uetype

-0.14

kÃ³w

-0.14

fait

-0.14

lla

-0.14

ynes

-0.14

Ø§Øµ

-0.14

POSITIVE LOGITS

ay

0.16

christ

0.16

ers

0.15

ate

0.15

ÐµÑĢÑĸ

0.14

rez

0.14

alous

0.14

 tablesp

0.14

 Torres

0.14

rag

0.13

Activations Density 0.037%

instances of the word "And" in various contexts

No Comments

No Known Activations