INDEX

Explanations

references to work-related topics and career issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 xtype

-0.16

 works

-0.14

ext

-0.14

ç¶

-0.14

;element

-0.14

panse

-0.14

ologies

-0.13

 Niet

-0.13

ifax

-0.13

bir

-0.13

POSITIVE LOGITS

 life

0.24

-life

0.23

life

0.23

 duties

0.23

 responsibilities

0.21

_life

0.21

 obligations

0.21

/home

0.19

-Life

0.19

åł´æīĢ

0.18

Activations Density 0.086%

references to work-related topics and career issues

No Comments

No Known Activations