INDEX

Explanations

expressions of assistance or aid

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

åĬŀçĲĨ

-0.14

ssue

-0.14

regon

-0.14

igit

-0.14

PELL

-0.13

chal

-0.13

Bundle

-0.13

angan

-0.13

ograd

-0.13

 Brothers

-0.13

POSITIVE LOGITS

 given

0.32

given

0.27

 already

0.26

 Given

0.25

 Already

0.24

Given

0.23

already

0.23

 GIVEN

0.22

 especially

0.21

 particularly

0.21

Activations Density 0.005%

expressions of assistance or aid

No Comments

No Known Activations