INDEX

Explanations

questions or references relating to uncertainty or inquiry about specific subjects

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

 them

-0.15

Jo

-0.15

yr

-0.14

ault

-0.14

à¥įà¤

-0.14

 bother

-0.14

rens

-0.14

 bothering

-0.14

aret

-0.14

eren

-0.14

POSITIVE LOGITS

 kind

0.21

 else

0.20

 kinds

0.19

 exactly

0.19

æł·çļĦ

0.18

 sort

0.18

 ELSE

0.17

kind

0.17

 type

0.17

 KIND

0.16

Activations Density 0.061%

questions or references relating to uncertainty or inquiry about specific subjects

No Comments

No Known Activations