INDEX

Explanations

articles and determiners highlighting key concepts in various statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

uckle

-0.16

iments

-0.16

ricks

-0.15

acies

-0.15

/apple

-0.15

imony

-0.15

 plethora

-0.14

ilerden

-0.14

é¹

-0.14

ittest

-0.14

POSITIVE LOGITS

 breeze

0.22

big

0.21

 matter

0.20

 necessity

0.20

 major

0.19

 valid

0.19

key

0.18

 snap

0.18

 must

0.18

 prime

0.18

Activations Density 0.140%

articles and determiners highlighting key concepts in various statements

No Comments

No Known Activations