INDEX

Explanations

phrases that discuss the impact or influence of actions and narratives in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

tra

-0.15

exo

-0.14

 Rowe

-0.14

<context

-0.14

archives

-0.13

Ø§Ø±ÙĬ

-0.13

ago

-0.13

áº¥p

-0.13

ìĤ°

-0.13

 Byron

-0.13

POSITIVE LOGITS

 ways

0.53

 Ways

0.39

way

0.34

ways

0.31

 somew

0.26

WAYS

0.25

.way

0.24

way

0.23

æĸ¹å¼ı

0.23

 sposÃ³b

0.23

Activations Density 0.173%

phrases that discuss the impact or influence of actions and narratives in various contexts

No Comments

No Known Activations