INDEX

Explanations

punctuation marks and their associated patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ibo

-0.17

 //!<

-0.15

Buf

-0.15

 Stuart

-0.15

 Warren

-0.14

AdminController

-0.14

+-+-

-0.14

Sid

-0.14

arda

-0.14

 saying

-0.14

POSITIVE LOGITS

udd

0.19

IGIN

0.16

ause

0.16

ahun

0.16

aised

0.16

á»ĵ

0.15

sonian

0.15

ignon

0.15

utex

0.14

anno

0.14

Activations Density 0.002%

punctuation marks and their associated patterns

No Comments

No Known Activations