INDEX

Explanations

punctuation marks, particularly commas and periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

oret

-0.15

cf

-0.15

seed

-0.15

-fw

-0.14

,“

-0.14

»¿

-0.14

rie

-0.14

ringe

-0.13

 alternate

-0.13

irs

-0.13

POSITIVE LOGITS

 tongue

0.19

ToPoint

0.18

quote

0.16

 quote

0.15

quier

0.15

agit

0.15

ideo

0.14

ê¸ī

0.14

 somewhat

0.14

aed

0.14

Activations Density 0.085%

punctuation marks, particularly commas and periods

No Comments

No Known Activations