INDEX

Explanations

references to depression and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

eger

-0.18

 micron

-0.16

RS

-0.15

 juice

-0.15

erm

-0.15

mi

-0.14

eric

-0.14

_frm

-0.14

elp

-0.14

er

-0.14

POSITIVE LOGITS

endent

0.21

(dep

0.20

dep

0.20

.dep

0.18

Dep

0.17

ford

0.17

 ÐºÑĢÑĭ

0.16

 dÃ©p

0.16

cies

0.15

artment

0.15

Activations Density 0.025%

references to depression and related terms

No Comments

No Known Activations