INDEX

Explanations

specific dates and historical events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilee

-0.15

Ã«n

-0.15

uess

-0.15

SEL

-0.15

ÐµÐ»Ðµ

-0.15

bero

-0.15

oÄį

-0.14

>NN

-0.14

'=>"

-0.14

CTL

-0.14

POSITIVE LOGITS

 mate

0.18

mate

0.17

 Mate

0.16

Mate

0.15

Ø§Ùģ

0.15

ade

0.15

<<<

0.15

atten

0.14

exels

0.14

illard

0.14

Activations Density 0.010%

specific dates and historical events

No Comments

No Known Activations