INDEX

Explanations

terms related to digital media formats and devices for accessing content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ouis

-0.16

ombok

-0.15

Ø·Ùĩ

-0.15

otos

-0.14

lom

-0.14

 piger

-0.14

åĨ

-0.14

çľī

-0.14

¦Ĥ

-0.13

afort

-0.13

POSITIVE LOGITS

ORB

0.16

jd

0.15

enci

0.14

nÃŃ

0.14

 Ø¬Ø±

0.14

Courier

0.14

ä»ĭ

0.14

 Germ

0.13

ten

0.13

ukan

0.13

Activations Density 0.019%

terms related to digital media formats and devices for accessing content

No Comments

No Known Activations