INDEX

Explanations

terms related to food and health services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ym

-0.21

yt

-0.18

addle

-0.17

inen

-0.16

upy

-0.16

alse

-0.15

 Bill

-0.15

 bill

-0.15

gr

-0.15

EB

-0.15

POSITIVE LOGITS

.asc

0.16

icker

0.15

omer

0.15

/Dk

0.14

_SO

0.14

.SO

0.14

çĸĨ

0.14

praak

0.14

arkan

0.14

(EFFECT

0.14

Activations Density 0.040%

terms related to food and health services

No Comments

No Known Activations