INDEX

Explanations

possessive pronouns and their associated references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ernote

-0.17

Wunused

-0.16

xdd

-0.15

_mD

-0.15

 Ð²ÑģÐ¿

-0.14

udu

-0.14

 grandchildren

-0.14

ellas

-0.14

(éĩĳ

-0.14

 Jaune

-0.14

POSITIVE LOGITS

 former

0.23

0.20

 fellow

0.19

 friend

0.18

aho

0.18

co

0.17

 another

0.17

 colleague

0.16

 previous

0.16

ada

0.16

Activations Density 0.065%

possessive pronouns and their associated references

No Comments

No Known Activations