INDEX

Explanations

instances of the word "And" used to connect thoughts or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

anes

-0.17

ught

-0.15

ural

-0.14

erties

-0.14

ighted

-0.14

strtolower

-0.13

mlink

-0.13

 Spar

-0.13

ova

-0.13

etric

-0.13

POSITIVE LOGITS

 zwar

0.15

isman

0.15

isd

0.15

reater

0.15

LLU

0.14

ÎµÎ¯

0.14

olean

0.14

ongo

0.14

jos

0.14

_atom

0.14

Activations Density 0.061%

instances of the word "And" used to connect thoughts or ideas

No Comments

No Known Activations