INDEX

Explanations

expressions related to skepticism and doubt about actions or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

zan

-0.19

elay

-0.14

ngr

-0.14

 zwar

-0.14

Ø¯Ø§ÙĨ

-0.14

_relative

-0.14

aily

-0.13

almost

-0.13

vier

-0.13

chein

-0.13

POSITIVE LOGITS

 anything

0.25

 ever

0.25

 anymore

0.24

 necessarily

0.24

any

0.23

 EVER

0.23

anything

0.21

 suddenly

0.21

 anybody

0.21

æľīä»Ģä¹Ī

0.21

Activations Density 0.149%

expressions related to skepticism and doubt about actions or potential outcomes

No Comments

No Known Activations