INDEX

Explanations

instances of the word "this" and related phrases

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

 ëĦ¤ìĿ´íĬ¸

-0.19

ohn

-0.16

Î¼Î¬

-0.15

arma

-0.14

jo

-0.13

ëį°ìĿ´íĬ¸

-0.13

ÎºÎ¬

-0.13

ingen

-0.13

idon

-0.13

POSITIVE LOGITS

 approach

0.22

 technique

0.21

 code

0.21

appro

0.20

way

0.20

 command

0.19

 operation

0.18

 functionality

0.17

 method

0.17

 function

0.16

Activations Density 0.116%

instances of the word "this" and related phrases

No Comments

No Known Activations