INDEX

Explanations

phrases indicating a wide variety or range of options or solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

åĢĭ

-0.14

ersed

-0.13

æŃ

-0.13

endum

-0.13

å°ĺ

-0.13

kich

-0.12

à¸±à¸¨

-0.12

 Harden

-0.12

ottie

-0.12

itt

-0.12

POSITIVE LOGITS

 wide

0.54

 broad

0.46

 range

0.43

 variety

0.42

 widest

0.40

 Wide

0.35

range

0.35

 ÑĪÐ¸ÑĢÐ¾Ðº

0.34

-wide

0.32

Wide

0.32

Activations Density 0.082%

phrases indicating a wide variety or range of options or solutions

No Comments

No Known Activations