INDEX

Explanations

words that begin with the letter 'w'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Helpers

-0.15

andest

-0.15

lake

-0.14

stras

-0.14

 DÃ¼z

-0.14

ibar

-0.14

ÙħÙĦØ©

-0.14

arie

-0.14

-0.13

POSITIVE LOGITS

0.22

ering

0.19

ideo

0.17

anj

0.16

nder

0.16

=w

0.16

jam

0.15

idd

0.15

itten

0.15

ingly

0.15

Activations Density 0.025%

words that begin with the letter 'w'

No Comments

No Known Activations