INDEX

Explanations

key historical events and their related implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Ð´Ð¾ÑĢ

-0.15

åĲ«

-0.15

icular

-0.15

 Keller

-0.14

acher

-0.14

pur

-0.14

isor

-0.14

onis

-0.14

haps

-0.13

kers

-0.13

POSITIVE LOGITS

 kola

0.16

#+#

0.15

ixo

0.15

ushi

0.15

$LANG

0.15

idlo

0.14

antu

0.14

Ø³ÙĦ

0.14

.undo

0.14

 voleb

0.13

Activations Density 0.127%

key historical events and their related implications

No Comments

No Known Activations