INDEX

Explanations

characters and elements related to storytelling or narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

inaire

-0.17

elin

-0.15

 ---------------------------------------------------------------------------↵

-0.14

ruc

-0.14

ikip

-0.14

lavÃŃ

-0.14

orgot

-0.14

Ð¾ÐºÑĢÐµÐ¼Ð°

-0.13

emma

-0.13

POSITIVE LOGITS

 nevertheless

0.28

 nonetheless

0.27

Nevertheless

0.18

 Nevertheless

0.16

åį»

0.15

 quickly

0.15

åį´

0.15

yet

0.15

 Nonetheless

0.15

zan

0.15

Activations Density 0.426%

characters and elements related to storytelling or narrative

No Comments

No Known Activations