INDEX

Explanations

references to specific chapters or sections in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

infeld

-0.17

adu

-0.15

CTS

-0.15

aidu

-0.15

nown

-0.14

ondon

-0.14

ikh

-0.14

ÙĲÙĨ

-0.14

/popper

-0.14

loys

-0.14

POSITIVE LOGITS

ought

0.18

 Shank

0.15

ESC

0.14

 newIndex

0.14

rag

0.14

stu

0.14

gil

0.14

´Ī

0.13

adin

0.13

Crud

0.13

Activations Density 0.251%

references to specific chapters or sections in a text

No Comments

No Known Activations