INDEX

Explanations

phrases that express likelihood or probability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

erot

-0.16

 maman

-0.16

uary

-0.15

Ð°ÑĢÐ°ÑĤ

-0.15

 Blanc

-0.14

Ã»t

-0.14

izu

-0.14

orna

-0.14

acro

-0.14

 Lies

-0.14

POSITIVE LOGITS

aison

0.16

0.15

 attend

0.15

gent

0.15

ooks

0.15

exual

0.15

 Attendance

0.14

ule

0.14

 Maid

0.14

Activations Density 0.016%

phrases that express likelihood or probability

No Comments

No Known Activations