INDEX

Explanations

occurrences of the word "stop" and related variations in both text and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ichten

-0.17

ÑĢÐ¸Ð²

-0.15

à¸²à¸ĺ

-0.15

erging

-0.15

erge

-0.14

stride

-0.14

egrate

-0.14

rees

-0.14

kv

-0.14

èĶµ

-0.14

POSITIVE LOGITS

per

0.23

lights

0.21

PING

0.21

-motion

0.21

over

0.20

page

0.20

gap

0.20

/start

0.19

pered

0.19

pping

0.19

Activations Density 0.029%

occurrences of the word "stop" and related variations in both text and programming contexts

No Comments

No Known Activations