INDEX

Explanations

pronouns and verbs that indicate action or state of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

oproject

-0.16

ÑĪÑĮ

-0.15

upy

-0.14

 Larger

-0.13

xCD

-0.13

zag

-0.13

celik

-0.13

 à¤ľà¤Ĺ

-0.13

_chg

-0.13

ombo

-0.13

POSITIVE LOGITS

 under

0.20

 Under

0.18

 effective

0.18

its

0.17

under

0.17

 Pref

0.17

Pre

0.17

 UNDER

0.17

 their

0.16

pre

0.16

Activations Density 0.014%

pronouns and verbs that indicate action or state of being

No Comments

No Known Activations