INDEX

Explanations

phrases that indicate an active process of progression or change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ucks

-0.19

asket

-0.15

inyin

-0.15

antt

-0.14

assen

-0.14

 downt

-0.14

aurus

-0.13

 Pres

-0.13

*</

-0.13

ottie

-0.13

POSITIVE LOGITS

illas

0.17

chal

0.16

_mC

0.16

 Malk

0.14

å§ĭ

0.14

¾

0.14

 Tubes

0.14

STEP

0.14

åľ

0.14

_mD

0.13

Activations Density 0.036%

phrases that indicate an active process of progression or change

No Comments

No Known Activations