INDEX

Explanations

instances of encountering or coming across various situations or problems

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

undler

-0.20

infeld

-0.17

cx

-0.16

 Freund

-0.15

åĢĻ

-0.14

ÑĢÐ°ÑĤ

-0.14

currentColor

-0.14

olah

-0.14

 MainAxisAlignment

-0.14

iterals

-0.14

POSITIVE LOGITS

er

0.18

ÄĽr

0.17

sgiving

0.16

exp

0.16

uze

0.16

heimer

0.16

ulse

0.15

uma

0.15

 Sterling

0.14

Activations Density 0.047%

instances of encountering or coming across various situations or problems

No Comments

No Known Activations