INDEX

Explanations

references to computer science and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

erialize

-0.19

ahren

-0.16

burgh

-0.16

shan

-0.15

Ã«l

-0.15

ifecycle

-0.15

erializer

-0.15

orsch

-0.15

TED

-0.14

TY

-0.14

POSITIVE LOGITS

IRO

0.26

 Lewis

0.18

CS

0.17

uci

0.17

irt

0.17

/cs

0.16

ny

0.16

IRT

0.16

pecially

0.15

cs

0.14

Activations Density 0.010%

references to computer science and related terminology

No Comments

No Known Activations