INDEX

Explanations

references to simplicity or straightforwardness in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

eenth

-0.16

ngr

-0.16

asco

-0.15

esis

-0.15

sel

-0.15

rif

-0.14

ulet

-0.14

ally

-0.13

POSITIVE LOGITS

ton

0.39

tons

0.39

xes

0.35

-minded

0.30

/simple

0.28

TON

0.27

ctic

0.27

 minded

0.26

st

0.24

/plain

0.22

Activations Density 0.033%

references to simplicity or straightforwardness in context

No Comments

No Known Activations