INDEX

Explanations

phrases related to user actions and interactions with technology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

\views

-0.16

-0.15

-0.14

-alist

-0.14

hod

-0.14

 ÑģÐ¼

-0.13

 clipped

-0.13

 Liberation

-0.13

POSITIVE LOGITS

 prompt

0.32

 directed

0.30

prompt

0.30

 prompted

0.28

 directing

0.27

 Prompt

0.27

 prompting

0.27

Prompt

0.26

 prompts

0.26

Directed

0.25

Activations Density 0.105%

phrases related to user actions and interactions with technology

No Comments

No Known Activations