INDEX

Explanations

words beginning with the letter 'c'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ookies

-0.17

trl

-0.16

li

-0.15

 catches

-0.15

sv

-0.15

/close

-0.15

 Cosmos

-0.15

craper

-0.15

ACHE

-0.15

lu

-0.15

POSITIVE LOGITS

apping

0.24

ensure

0.23

 lear

0.22

ros

0.20

oda

0.20

ensored

0.20

ursive

0.20

oter

0.20

unj

0.19

orte

0.19

Activations Density 0.033%

words beginning with the letter 'c'

No Comments

No Known Activations