INDEX

Explanations

instances of the word "put" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

_invite

-0.16

-0.15

Setup

-0.15

GGLE

-0.15

Ð¾ÑĤÐ°

-0.15

èĩ´

-0.14

 trick

-0.14

desk

-0.14

eter

-0.14

POSITIVE LOGITS

put

0.25

put

0.24

 effort

0.22

 putting

0.22

 puts

0.22

 Putting

0.21

 aside

0.20

Put

0.20

 emphasis

0.20

PUT

0.20

Activations Density 0.064%

instances of the word "put" and its variations in various contexts

No Comments

No Known Activations