INDEX

Explanations

instances of past tense verbs and phrases associated with completed actions or contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aget

-0.18

tridge

-0.17

utilus

-0.16

jeta

-0.16

unas

-0.15

íĺĳ

-0.15

ê¸ī

-0.15

 íĺĳ

-0.15

iid

-0.14

misc

-0.14

POSITIVE LOGITS

 guest

0.24

 guests

0.24

 Guests

0.24

 presence

0.24

Guest

0.24

 Guest

0.20

guest

0.20

 recip

0.20

 attendance

0.19

 undergoing

0.19

Activations Density 0.010%

instances of past tense verbs and phrases associated with completed actions or contributions

No Comments

No Known Activations