INDEX

Explanations

numerical data and timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.16

illard

-0.14

wer

-0.14

ardin

-0.14

agan

-0.14

olt

-0.13

immer

-0.13

athers

-0.13

Raw

-0.13

 tÆ°á»£ng

-0.13

POSITIVE LOGITS

æ´²

0.17

PR

0.17

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.16

etur

0.16

imitive

0.15

zano

0.15

afone

0.14

vais

0.14

PR

0.14

coles

0.14

Activations Density 0.005%

numerical data and timestamps

No Comments

No Known Activations