INDEX

Explanations

non-zero formatted numerical data or entries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

elf

-0.17

undra

-0.16

sdale

-0.14

eten

-0.14

-0.13

å²Ĺ

-0.13

TRA

-0.13

 Ð§Ð¸

-0.13

urile

-0.13

POSITIVE LOGITS

archives

0.15

olatile

0.15

 Archives

0.15

 archives

0.15

pter

0.14

poon

0.14

autiful

0.14

imetype

0.14

znik

0.13

ReturnValue

0.13

Activations Density 0.000%

non-zero formatted numerical data or entries

No Comments

No Known Activations