INDEX

Explanations

numerical data and references to organizations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

urette

-0.16

 æ¼

-0.15

ãģ°ãģĭãĤĬ

-0.14

ucid

-0.13

eya

-0.13

pend

-0.13

imit

-0.13

Ø¶Ùħ

-0.12

ÑĤÑİ

-0.12

POSITIVE LOGITS

¬ģ

0.14

 scre

0.14

ableObject

0.13

iator

0.13

aeda

0.12

acific

0.12

://

0.12

clas

0.12

ision

0.12

Activations Density 0.205%

numerical data and references to organizations or entities

No Comments

No Known Activations