INDEX

Explanations

references to a specific theme or topic, likely related to a ceremony or event

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

kers

-0.16

olem

-0.14

strtolower

-0.14

Ð¾ÑģÐº

-0.14

Application

-0.14

ihil

-0.13

arde

-0.13

asure

-0.13

ŀ

-0.13

POSITIVE LOGITS

quot

0.19

apos

0.17

nbsp

0.16

 tinder

0.16

Charsets

0.16

amp

0.16

ãĤīãģĦ

0.15

 ########.

0.15

ceipt

0.15

Activations Density 0.004%

references to a specific theme or topic, likely related to a ceremony or event

No Comments

No Known Activations