INDEX

Explanations

specific historical terms and significant events

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

 crackers

-0.17

pedia

-0.17

 McKin

-0.16

 ÐĴÐ¸Ðº

-0.15

phylum

-0.15

 Kitty

-0.14

ugen

-0.14

\/\/

-0.14

 Mediterr

-0.14

ohana

-0.14

POSITIVE LOGITS

Nov

0.22

Mus

0.22

 Grand

0.22

boy

0.21

Suz

0.21

 Princip

0.20

boy

0.19

Opr

0.19

 Pere

0.19

 Lith

0.19

Activations Density 0.016%

specific historical terms and significant events

No Comments

No Known Activations