INDEX

Explanations

references to research studies and analytical proofs

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

Emp

-0.15

 mediums

-0.15

Emp

-0.14

áº¡ch

-0.14

ager

-0.14

 empir

-0.14

 ìĥģ

-0.14

 empirical

-0.13

odom

-0.13

.dx

-0.13

POSITIVE LOGITS

 comb

0.25

 ÄĮech

0.21

ax

0.20

 functor

0.20

 Functor

0.19

 algebra

0.18

 obstruction

0.18

 geometric

0.18

Gro

0.18

 machinery

0.18

Activations Density 0.116%

references to research studies and analytical proofs

No Comments

No Known Activations