INDEX

Explanations

phrases indicating a small quantity or limited number of items

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

amen

-0.17

uet

-0.14

rej

-0.14

uto

-0.14

ORIES

-0.14

ent

-0.14

 only

-0.14

gang

-0.13

ned

-0.13

POSITIVE LOGITS

 dozen

0.24

/all

0.17

ibrator

0.16

 mÃ¡lo

0.16

kiye

0.16

 Ð´ÐµÑģÑıÑĤ

0.16

äººçļĦ

0.16

ynom

0.15

-times

0.15

 dalÅ¡ÃŃch

0.14

Activations Density 0.041%

phrases indicating a small quantity or limited number of items

No Comments

No Known Activations