INDEX

Explanations

variations of the word "achieve" and other related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rr

-0.19

sk

-0.16

enstein

-0.15

ono

-0.15

otlin

-0.14

rh

-0.14

rtc

-0.14

enburg

-0.14

casts

-0.14

issan

-0.14

POSITIVE LOGITS

ving

0.42

ved

0.39

vers

0.37

vable

0.36

ve

0.36

vements

0.35

ves

0.33

ver

0.32

vement

0.31

iving

0.27

Activations Density 0.019%

variations of the word "achieve" and other related terms

No Comments

No Known Activations