INDEX

Explanations

frequent occurrences of the word "the."

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

AA

-0.17

VV

-0.15

 guard

-0.15

ter

-0.15

am

-0.15

au

-0.15

ura

-0.14

mo

-0.14

ree

-0.14

POSITIVE LOGITS

 sake

0.28

 purposes

0.26

geries

0.19

zar

0.17

OfDay

0.17

aylight

0.17

OfString

0.16

unately

0.16

 Mitar

0.15

beeld

0.15

Activations Density 0.111%

frequent occurrences of the word "the."

No Comments

No Known Activations